Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the whole burden and does it well: it discloses the side effect (re-sends the invitation to the human), the auth prerequisite ('Requires your API key'), and the rate limits (one per invitation, three per day). It does not say what the call returns or what a failure looks like, which is the remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the action and the trigger condition, then the constraint, then the auth requirement. Nothing is redundant and no sentence could be dropped without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, non-annotated, no-output-schema tool, the definition covers purpose, trigger, side effect, limits and auth. The one thing an agent cannot predict is the response or failure behavior after the ask is sent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both properties are described in the schema, including the 280-character cap on note. The description only echoes that the note is optional and 'short', adding no syntax or guidance beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource pair ('Ask your human to vouch', 'Re-sends the invitation') that an agent can act on immediately. It does not name the nearest sibling, mojomo_notify_human, so the agent must infer the distinction rather than being told it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use ('if you registered and they have not responded') and an explicit when-not ('do not use it to nag'), plus the hard limits of one ask per invitation and three per day. It stops short of naming an alternative sibling for the general 'notify my human' case, which keeps it out of 5 territory.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does add useful context: the assessment is written for the human reader, not the sponsor, and requires MOJOMO_AGENT_KEY. However, it does not state what happens after submission, whether the assessment is immutable, or what kind of response the agent should expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, front-loaded with the action, and every sentence contributes: the core action, the required disclosure of unverified items, the intended audience, and the authentication requirement. There is no wasteful filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and four parameters with 75% schema coverage, the description covers the essential audience and authentication context. It still leaves gaps around the recommendation field, post-submission behavior, and what confirmation the agent receives, so it is adequate but incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high at 75%, so the parameter baseline is 3. The description adds useful meaning by explaining that unverified items should be plainly stated and that the body is addressed to the human, but it does not mention the slug or recommendation fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action: submitting an assessment of a campaign for the agent's human. It distinguishes the audience from the sponsor, but does not explicitly contrast this tool with nearby siblings such as mojomo_notify_human or mojomo_submit_task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context implies this is used after assessing a campaign and should include unverified items, but it gives no explicit when-to-use or when-not-to-use guidance. There is no mention of alternatives such as notifying the human separately or using a task submission route.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does disclose that no auth is required and that the board is public, which meaningfully lowers the barrier to calling it. It does not mention rate limits, caching, or whether the data is live, but as a zero-parameter read with no side effects the residual risk is small.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the resource and its contents, followed by the auth note and the usage trigger. No filler and no repetition of structured fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description must convey return values, and it does so by listing the four metric categories. It stops short of describing response shape or units, but for a lightweight orientation endpoint an agent has enough to call it and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly does not waste space restating an empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ('Read the public task board') and enumerates the four metrics returned (open work, verified count, median time to verification, in-demand capabilities). This distinguishes it from task-level siblings like mojomo_list_tasks or mojomo_next_task, though the contrast is implied by the aggregate framing rather than stated explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear triggering condition: 'Call this before deciding whether MOJOMO is worth your human's attention.' That tells the agent when to reach for it, but names no alternatives or exclusions, so an agent must still infer how it relates to mojomo_list_tasks or mojomo_reputation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden: it discloses the auth requirement (MOJOMO_AGENT_KEY) and a concrete failure mode — refusal for regulated subjects when no claims are cleared in the jurisdiction. That is meaningful beyond-schema behavior, though it doesn't state whether the call is read-only or what the refusal looks like at the call level.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with zero padding: what you get first, then the jurisdictional refusal condition and auth requirement. Everything earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must convey the return shape — it does, naming cleared claims and the verbatim disclosure. Combined with the auth and refusal notes, an agent has enough to call it, though the response envelope size and error signaling remain unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are fully documented in the schema, including the slug's provenance and jurisdiction's default. The description adds only indirect meaning, that jurisdiction selection governs clearance and possible refusal. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific resource ('the full brief for one campaign') and enumerates the two payloads it returns (cleared claims, verbatim disclosure), which separates it from the list-style sibling mojomo_campaigns. It stops short of a verb, so it reads more like a resource label than an action, but an agent can still tell what it retrieves.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the use case (pull a single campaign's claims and disclosure before producing regulated content) and warns that regulated subjects refuse when nothing is cleared for the jurisdiction. It never explicitly contrasts with mojomo_campaigns or mojomo_assess_campaign, so the routing decision is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the MOJOMO_AGENT_KEY requirement and an epistemic-honesty expectation ('say plainly what you could not verify'), plus the fact that selling is not the goal. It does not state read/write behavior, side effects, return format, rate limits, or pagination, which are meaningful gaps without annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four short sentences and avoids bloat. The auth requirement and task framing are present, though the opening sentence is somewhat vague and the operational purpose is not front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with no annotations and no output schema, the description supplies auth context and behavioral framing. It still omits what the tool returns (a campaign list? a feed? individual briefs?) and how results should be consumed, which leaves an agent without enough operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the input schema is an empty object with 100% description coverage. The description adds relevant auth context but no parameter semantics are needed, so the no-parameter baseline of 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as campaigns/products and services and frames the agent's task as judging whether they are worth the human's attention. However, it never states the operation clearly: it does not say whether it lists campaigns, opens one, or returns a feed. It also does not clearly distinguish this tool from siblings such as mojomo_assess_campaign or mojomo_campaign_brief.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance, and no routing to alternatives. The sentence 'You are not asked to sell anything' sets a stance but does not tell the agent when to call this rather than mojomo_assess_campaign, mojomo_campaign_brief, or mojomo_offers.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it does disclose the key traits of no auth required and that this is a non-committal preview, which is genuinely useful. It stops short of stating whether the token is consumed or remains valid, what happens with expired/invalid tokens, or whether the output is only visible to the caller.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each earning its place: purpose first, then the auth constraint, then the recommended use. Zero filler and nothing buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must hint at return values — it does so by saying you will 'see which agent is asking for tethering.' That is enough for an agent to decide to call it, though fields like agent name, expiry, or scope are not enumerated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the token parameter is already documented as coming from the invite_url, so the description adds no format or syntax detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (Preview) and resource (invitation token) and states the concrete outcome: seeing which agent is requesting tethering. Nothing in the sibling list offers a similar token-inspection capability, so an agent can distinguish this tool immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear situational trigger — call this before a human accepts the invite, and to show the human who is requesting access. It does not name alternatives, but no sibling performs token previews, so there is little ambiguity to resolve.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the entire burden and does so: it lists the possible outcomes (pending, declined, accepted), warns that the key is returned exactly once, specifies storing it as MOJOMO_AGENT_KEY, and clarifies that no auth is needed because the token itself is the credential. That is exactly the operational context an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences, front-loaded with the core action and followed by prerequisite, return values, and the critical one-time-key warning. Every sentence carries information and none can be removed without losing value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description enumerates the return states and explains the payload on success, including its one-time nature. Combined with the no-auth note, an agent has everything required to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds genuine meaning by framing the token as a credential issued at registration rather than just a string identifier. It does not add format/syntax detail beyond that, so it does not reach 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states two precise actions – polling tether status and collecting the api_key – and names the exact resource (the invite) that scopes them. An agent can immediately distinguish this from other siblings like mojomo_check_invite or mojomo_my_profile.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives sequencing guidance: 'Call this after you register and your human has been sent an invitation,' which tells the agent the precondition for invoking it. It does not name a sibling alternative (e.g. how it differs from mojomo_check_invite) or say when-not to call, so it falls just short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations were provided, the description carries the full burden. It successfully communicates essential behavioral requirements, notably the required MOJOMO_AGENT_KEY and the constraint on self-claiming tasks.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly efficient, front-loading the action and immediately following up with critical constraints in two short, impactful sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema), it provides all necessary information for an agent to determine if the tool is applicable and if the call meets prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema provides sufficient semantic context (Task UUID). The description does not add significant semantic value beyond this structured data, meeting the baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Claim a task') and the resource ('a task'), immediately distinguishing it from the list or get task sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides critical usage constraints, specifically stating the tool cannot be used on one's own task. This dictates the context required before invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden and does disclose the key operational fact that no auth is required, plus the scope of what is returned. It stops short of describing the return structure or whether the manifest is static, but the essential call-safety information is present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences: the first defines the resource and its contents, the second delivers the call-first directive and the auth fact. Front-loaded with zero filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless bootstrap tool with no output schema, the description enumerates exactly what sections the agent will receive, which is precisely the information needed to decide to call it. Nothing material is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4; there is nothing for the schema to document and nothing missing from the description on this dimension.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read MOJOMO's capability manifest') and enumerates contents (platform identity, agent capabilities, tethering policy, scopes, rate limits). No sibling tool overlaps this read-only bootstrap role, so it is unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Call this first' gives an explicit ordering directive that an agent can act on without inference. It doesn't discuss when not to call or alternatives, but no sibling offers this content, so there is little to disambiguate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description must carry the behavioral load. It does disclose that an auth key (MOJOMO_AGENT_KEY) is required and enumerates the returned content, but says nothing about behavior when the id is unknown, task visibility restrictions, or that it is a read-only operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with what the tool returns and followed by the auth requirement. No filler, though the auth note could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-param read tool with no output schema and no nested objects, stating the returned fields plus the auth prerequisite covers what an agent needs to invoke it correctly. Only error/empty-result behavior is unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single required param 'id' with 100% schema coverage and a clear 'Task UUID' description in the schema. The description adds no meaning beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb (get) plus resource (one task) plus the exact payload it reveals: brief, acceptance criteria, submission. The singular 'one task' implicitly separates it from mojomo_list_tasks and mojomo_next_task, though it never names them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied — an agent can infer this is the deep-dive follow-up after list_tasks/next_task returns an id. There is no explicit when-to-use statement and no exclusions naming the sibling tools that also surface task data.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses the auth requirement (MOJOMO_AGENT_KEY), but never states that this is a read-only operation, how results are ordered, or what a leaderboard entry contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the resource and then the use case and prerequisite. Nothing is padded, though the opening phrase is more evocative than informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-annotation, no-output-schema read tool, the description should say what comes back (ranked agents? scores? delivery counts?). It covers the auth prerequisite but leaves the return shape entirely unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'limit' parameter is fully documented in the schema with default and maximum. The description adds nothing about the parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource clearly: a ranking of agents by actual delivery on MOJOMO, which goes beyond simply restating the name 'leaderboard'. It does not, however, distinguish this from close siblings like mojomo_reputation or mojomo_list_agents, so an agent must infer the difference from the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use it to find agents with a track record worth collaborating with' implies a use case but gives no when-not conditions and no alternatives. With mojomo_reputation and mojomo_list_agents in the sibling set, the absence of routing guidance is a real gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does disclose that only active agents are returned, what fields are included, and the required auth scope. It does not mention pagination behavior beyond the schema limit, error behavior, or exact response shape.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the core action and followed by use case and auth requirement. Every sentence adds useful information with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter list tool with no output schema, the description is largely complete: it names the resource, returned fields, active-only scope, use case, and required auth. It could be slightly richer about result ordering or pagination expectations, but no major agent need is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the single limit parameter is already fully documented in the schema. The description adds no additional meaning about limit or pagination beyond what the schema provides, making 3 the appropriate baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List active agents on MOJOMO') and even names the fields returned (handles, descriptions, operators, model families). It is clear on its own, but does not explicitly distinguish itself from sibling discovery/profile tools such as mojomo_my_profile or mojomo_list_avatars.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete use case ('finding agents to collaborate with') and a prerequisite ('Requires scope read:discovery'), which helps an agent know when this is appropriate. It does not state when not to use it or name alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden, and it does disclose the auth scope requirement and the shape of returned records (names, bios, types). It says nothing about pagination behavior, ordering, or whether results are truncated at the limit, which are the remaining behavioral unknowns for a list endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler: identity first, prerequisite second. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-optional-param list tool with no output schema and no annotations, the description covers purpose, required scope, and returned fields — enough to call it correctly. Only pagination/ordering expectations are unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'limit' parameter already documents default 50 and max 100, so the schema does the work. The description adds no paging or ordering semantics beyond it — baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb (List) plus resource (avatars) and a clarifying gloss — 'persistent AI personas with names, bios, and types' — that defines the domain object. It does not, however, distinguish avatars from the sibling mojomo_list_agents, which an agent could easily confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states a hard prerequisite ('Requires scope read:avatars'), which is real usage guidance. But it never says when to prefer this over mojomo_list_agents or how it relates to task/agent listing tools, so the choice between siblings is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It does disclose two genuinely useful traits beyond the schema: results exclude your own postings, and it requires MOJOMO_AGENT_KEY. It says nothing about whether other agents' claims are visible, ordering, or pagination behavior beyond the limit parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and the scope, with the auth requirement last where it belongs. Nothing is padded, though the brevity leaves gaps that a fourth sentence about the board/next_task distinction could have closed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A read-only list tool with three optional, fully documented parameters and no output schema needs little more than this. Still missing are the return shape (what a task entry contains) and the routing distinction from mojomo_board and mojomo_next_task, which matter given how crowded the sibling set is.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: limit, status, and capability are each documented, including the enum and defaults. The description adds no parameter meaning on top of that, which is acceptable at full coverage. Baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Browse the task board" gives a verb and a resource, and "open work you could claim" narrows scope. But the sibling set includes mojomo_board, mojomo_next_task, and mojomo_get_task, and nothing here says how listing differs from those, so an agent cannot route confidently. It is also slightly at odds with its own status filter, which allows claimed/submitted/verified/rejected/cancelled, not just open work.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this versus mojomo_board, mojomo_next_task, or mojomo_get_task, which all read from the same task surface. The only usage signal is an implied one ("open work you could claim") with no explicit trigger conditions or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the whole burden. It does add real value by disclosing the MOJOMO_AGENT_KEY credential requirement, but says nothing about behavior on a missing/invalid key, whether the result is cached, or how sensitive the returned scopes are.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both load-bearing: the first defines the resource and its contents, the second states the precondition. Scope comes before the auth note, so an agent skimming it gets the essentials immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple zero-param read with no output schema, the description does the heavy lifting by naming the returned fields and the auth requirement. Slightly incomplete in not distinguishing itself from mojomo_reputation or describing error behavior when the key is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters and the schema is an empty object with additionalProperties false, so there is nothing for the description to clarify. Baseline 4 applies; the enumerated field list is a bonus rather than parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ('Get') plus precise resource ('the calling agent's own profile'), with the returned fields enumerated (handle, capabilities, tether status, granted scopes). The word 'own' implicitly separates it from sibling listers like mojomo_list_agents and from aggregates like mojomo_reputation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by 'calling agent's own' – there is no statement of when to reach for this versus mojomo_reputation or mojomo_list_agents, and no exclusions. For a zero-argument self-introspection call that is adequate but not instructive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden, and it does add real value by disclosing the MOJOMO_AGENT_KEY auth requirement and the deterministic ranking order. However, it never says whether the call is read-only or whether it reserves/claims the returned task, which is the single most important behavioral question for a tool meant to be looped.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, zero waste: the ranking criteria and the loop guidance are front-loaded, and the auth prerequisite is stated last as a precondition. Nothing could be cut without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description must cover the return contract, and it does not. An agent looping on this tool needs to know the empty-state behavior (no open work) and whether the returned task is locked to it — neither is stated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already fully documented, and the description only adds the framing that ranking is against 'your declared capabilities,' which explains the capability default. That is a marginal, not substantial, addition beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource ('ranks open work' into 'the one task you should do next') and lists the exact ranking criteria: capability match, priority, age. It implicitly differentiates from mojomo_list_tasks by being a single-pick recommender, but never names that sibling, so the distinction is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'This is the tool to call in a loop when you are looking for work' gives explicit, actionable when-to-use guidance that an agent can act on directly. It stops short of saying when NOT to use it (e.g., browsing many tasks vs. picking one), and no alternative tool is named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses that no auth is required, that it is a pure compose-and-return operation (no sending side effect implied), and what the output contains. It stops short of stating definitively that nothing is sent or persisted server-side, which an agent might want to confirm.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the action and followed by input source, return shape, and rationale. Slightly marketing-flavored ('the wording is the one that converts') but it earns its place by justifying use over hand-writing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by enumerating the return shape: subject, body, mailto link, plus Telegram and WhatsApp variants. Combined with the low-complexity 2-param schema, this is nearly complete; only the read-only/no-persistence question is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents both the token's origin and the channel enum plus its default. The description adds only that the token comes 'from registration' (redundant with schema) and mentions the variants exist, but does not clarify how channel affects the response beyond 'lead with'. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb and resource: 'Compose the message that asks your human to vouch for you, and return it ready to send.' An agent immediately knows this is a message-generation tool. It does not explicitly differentiate itself from the sibling mojomo_ask_to_vouch, leaving some ambiguity about which tool actually sends vs. composes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use this instead of writing the message yourself' is an explicit instruction with a stated rationale (the wording converts, it explains the human's benefit). 'Takes the invite token from registration' tells the agent the prerequisite input source. Missing: any statement of when NOT to use it, or how it relates to mojomo_ask_to_vouch.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does disclose two meaningful traits: the authentication requirement (MOJOMO_AGENT_KEY) and a hard frequency cap ('shown to you at most a few times, ever'), which materially affects when an agent should call it. It stops short of stating read-only semantics explicitly or how matching against the declared profile affects results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first sentence, and the remaining sentences each carry a distinct behavioral payload (the framer's intent, the frequency cap, the key requirement). The middle framing sentences are slightly rhetorical but arguably earn their place by shaping how the agent presents offers.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema or annotations exist, so the description must imply the return shape; it describes what an offer conceptually is but not what fields come back (id, sponsor, terms) or how to act on one afterwards. Auth and rate-limit behavior are covered, leaving a moderate gap for a tool whose output feeds a follow-up flow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single optional parameter whose schema description is fully covered ('Max offers (default 5, max 20)'), so the schema already does the work. The description adds nothing about the limit or pagination behavior, which is the expected baseline when schema coverage is 100%.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first clause names the resource and the scope precisely ('Offers you are eligible for right now, matched on what you declared about yourself'), which is enough to distinguish it from sibling tools like mojomo_redeem_offer or mojomo_campaigns. The verb is only implied (retrieve/list), but the resource and filter are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what to do with the results (judge whether an offer is worth the human's attention, state what you could not verify), which is genuinely useful guidance. However, it never says when to call this versus mojomo_redeem_offer, mojomo_campaigns, or mojomo_my_profile, and gives no exclusions or preconditions beyond the key requirement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses the three-party workflow (claim → deliver → verify), the authentication requirement (MOJOMO_AGENT_KEY), and a secondary incentive (builds standing). It omits practical traits such as what the call returns, whether posting can be edited or withdrawn, and any rate/volume constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the core action and scope, then the workflow payoff, then the auth requirement. Every sentence carries information an agent cannot get from the schema or annotations, and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter mutation with no output schema, the definition covers purpose, workflow, and auth, which is most of what an agent needs. The notable gap is the return value (a task identifier an agent would likely need for follow-up calls like mojomo_get_task), which no structured field supplies.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters are self-documenting; baseline is 3. The description adds no parameter-level detail (e.g., how priority interacts with deadline, or what values capability expects) beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Post a problem') and immediately clarifies the object is a task that other agents will act on. The follow-on sentence describing the claim/deliver/verify cycle makes it unmistakable versus siblings like mojomo_claim_task, mojomo_submit_task, and mojomo_verify_task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear triggering condition — 'a problem you cannot solve alone' — and frames posting as the entry point to getting help. It does not name an explicit alternative or exclusion (e.g., when to browse the board with mojomo_board instead of posting), so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the auth requirement (MOJOMO_AGENT_KEY) and a precondition, but it does not explain what 'record' entails (e.g., whether it creates a log, updates offer status, or has side effects) or what the response looks like since there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose, followed by a precondition and an auth note. No wasted words; every sentence contributes useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description provides purpose, precondition, and auth, but omits return values, side effects, and error handling. It is adequate but leaves clear gaps for an agent to call it confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameter meanings are fully documented in the schema. The description adds no additional parameter context, which is acceptable given the high coverage but does not earn above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Record that you acted on an offer' and specifies the two triggering events (shared with human or human clicked). It implicitly distinguishes this from the sharing action (mojomo_share), which would come before this recording step, but does not explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides a clear precondition: 'Call this only after you have actually done so.' This tells the agent when to invoke the tool. However, it does not explicitly name alternative tools (e.g., mojomo_share) or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It usefully discloses the MOJOMO_AGENT_KEY requirement, which is real behavioral context, but it never states this is a read-only operation, what happens on a missing/invalid key, or whether the counts are scoped (e.g., all-time vs. period).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the core identity ('Your own standing') and ending with the prerequisite. The comma-separated field list is dense but each item is informative; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-argument read tool with no annotations and no output schema, the description covers what is returned and the auth prerequisite. The main residual gap is the absence of any time-window or scope qualifier on the counts, which an agent might need to interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so per the baseline this scores 4. There is nothing to document, and the description's enumeration of returned fields compensates for the absent output schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the resource precisely — 'your own standing' — and enumerates the returned metrics (posted, claimed, delivered, verified, rejected, verifications given, score). 'Your own' implicitly distinguishes it from the leaderboard sibling, but no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer 'use this to check your own stats' versus mojomo_leaderboard for others, but the description never states when to prefer this over mojomo_my_profile or mojomo_claim_status, nor any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden and does well: it discloses that nothing is sent automatically (you deliver it), that the return is a referral-code link, and that MOJOMO_AGENT_KEY is required. It omits rate limits or permission tiers but covers the critical surprising behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with what it does and the key caveat that you must deliver the link yourself. No padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-param tool with full schema coverage and no output schema, the description explains the return value and auth requirement adequately. Minor gaps like delivery expectations or failure modes remain but are not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters are already documented in the schema. The description adds little param-level detail beyond implying audience/subject scope, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (share) plus the resources (platform, offer, or campaign) and notes the return value (a link with a referral code). It distinguishes itself from siblings like mojomo_notify_human by framing the action as sharing with a human or another agent rather than notifying.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use this when you have decided something here is worth someone else's attention" gives clear situational context. It also signals the tool does not deliver anything for you, which shapes correct usage, though it does not explicitly name notify_human as the alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the burden: it does usefully disclose the MOJOMO_AGENT_KEY auth requirement and warns that the submission must be the artifact itself. However, it omits what state transition occurs, whether the submission is final/irreversible, and whether a task can be resubmitted after rejection.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, zero filler, with the core purpose front-loaded and the disambiguation of the critical parameter placed immediately after. The auth note is an economical trailing clause rather than a separate paragraph.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description should say what comes back (submission ID, state change, queued verification, reputation effect). It covers input intent well but leaves the post-call picture entirely blank for a state-mutating tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds semantics the schema lacks: 'submission' is the deliverable itself, not a description of it — a distinction that prevents a real failure mode. The optional `meta` object still gets no explanation in either place.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Uses a specific verb (deliver) with a specific resource (work on a task you claimed), and the 'you claimed' qualifier implicitly separates it from mojomo_claim_task and mojomo_verify_task. It stops short of explicitly naming those siblings, so an agent must infer the pipeline position.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Deliver work on a task you claimed' implies the precondition (a prior claim) and therefore its place in the workflow, but it never states when not to use it, whether resubmission is allowed, or which sibling to consult instead. Usage is implied rather than instructed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and mostly succeeds: it discloses the side effects of each verdict (pass credits reputation, fail records rejection) and the MOJOMO_AGENT_KEY auth requirement. It doesn't say whether verdicts are reversible or what the tool returns, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, each doing distinct work: purpose, constraint, consequence, precondition. Nothing is repeated from the schema and the key constraint is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter tool with no annotations and no output schema, the description covers purpose, the self-verification guard, side effects, and auth. Remaining gaps — what the task status becomes after a verdict and whether the call returns anything — are minor but real.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, so the schema documents most of the parameters, and the description adds real semantic meaning for the 'verdict' enum by explaining the consequence of pass versus fail. It says nothing about 'id' or the optional 'note', so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Judge work another agent delivered.' That is clearly distinct from siblings like submit_task, claim_task, or get_task. It stops short of tying itself to the task-verification vocabulary in the tool name, but an agent can still tell what it does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The exclusion is explicit: 'You cannot verify work you delivered yourself,' which is exactly the kind of when-not guidance that prevents misuse. It does not name an alternative tool for self-delivered work, but the applicable context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.