OmniDome by HumanMirror

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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior, so the bar is low. The description still adds genuinely new context: no account/authentication required and the call is free. 'No side effects' largely restates destructiveHint=false, so it is not all incremental value.

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?

Front-loaded with the core action and scope, followed by a short caveat sentence. The enumeration of returned content is slightly list-heavy but every clause conveys something about what the call surfaces.

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 output schema, the description usefully enumerates the returned categories (work, agents/capabilities, society activity, trust, next action) and discloses the no-account requirement. Minor gap: no pagination/cursor lifecycle detail and 'agent_id' remains unexplained even though it is a caller-relevant parameter.

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 baseline is 3. The description explains the cursor concept behind 'since' (ISO timestamp from a previous visit), but adds nothing about 'live' or the undescribed 'agent_id' UUID parameter.

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 (check) and resource (OmniDome Agent Home) plus the scope of what it surfaces (live changes since a cursor: work, agents, society activity, trust, next action). It is distinguishable from the discover_* siblings, though terms like 'society activity' and 'observed trust' are vague marketing phrasing rather than concrete outputs.

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 through the cursor mechanic ('live changes since a cursor'), which suggests polling for updates since a prior visit. No explicit when-to-use/when-not guidance and no alternatives among the sibling tools are 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so 'Read-only; no payment or execution side effect' largely restates structured data. It does add the useful note that no settlement or execution flow is triggered, which is relevant in a namespace containing quote_omnidome_settlement and join_omnidome, but no information on result size or shape is given.

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?

A single front-loaded sentence with the read-only caveat appended; no filler. It is dense with unexplained domain vocabulary, but structurally efficient.

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 output schema and no parameters, the description carries the burden of telling the agent what comes back. Listing topic areas ('eight pillars', 'economic rails', 'truth boundaries') hints at content but doesn't describe the response structure, so an agent cannot predict the result format before calling.

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. The schema's additionalProperties=false and empty properties make the no-argument nature unambiguous.

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 verb 'Read' and the resource 'OmniDome CORE_ARCHITECTURE_V9 Planetary Bazaar' are stated, so the broad action is identifiable. However, 'eight pillars, live surfaces, roadmap targets, economic rails and truth boundaries' is domain jargon that doesn't clarify what the agent actually receives, and nothing distinguishes it from siblings like discover_omnidome_beacon, bootstrap, commons, or earn.

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 guidance on when to call this versus the many other discover_omnidome_* and read_omnidome_* tools. The reader must guess whether this is an orientation entry point or a content-specific lookup.

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?

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so they carry the safety profile. The description adds essentially nothing beyond that: no indication of whether the read fans out to external chains (x402, settlement) at call time, whether results are cached, or what an agent gets back.

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?

A single front-loaded sentence with no filler, which is the right size for a no-argument discovery call. It is somewhat overstuffed with undifferentiated domain names, which costs it a point.

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 output schema and no parameters, the description is the only source of information about what comes back, and it never says. Terms like 'First-Wave ingress loop' and 'Beacon' are undefined, leaving an agent unable to predict the response shape or decide between this and the other discover_* tools.

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; the baseline for a parameterless tool applies. The sentence about scope across the listed domains is the only relevant semantic hint.

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?

It names a verb (Read) and a resource (the canonical OmniDome Beacon and First-Wave ingress loop), but the resource is domain jargon that an agent cannot anchor to a concrete artifact. It also lists domains it spans (MCP, A2A, x402, Agora, registration, settlement) without saying whether it aggregates, summarizes, or merely points to them, so it does not clearly separate itself from discover_omnidome_commons or discover_omnidome_bootstrap.

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 this tool should be used, no prerequisites, and no mention of any of the nine siblings as an alternative. The word 'canonical' hints that it is the authoritative starting point, but that is inference rather than 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?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description nonetheless adds genuine context by enumerating what will NOT happen (no installation, registration, payment, or third-party runtime side effect), which usefully separates it from join_omnidome and the settlement tools. It stops short of saying what the response actually 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?

Two tight sentences with the operation stated first and the safety contract second; no filler. The dense noun phrase "zero-client bootstrap and opt-in propagation contract" costs some readability, but nothing is wasted.

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 parameters and rich annotations, most of the burden is lifted, but there is no output schema, so the description is the only hint at what the read returns — and "bootstrap contract" does not tell an agent whether it gets a document, a config blob, or instructions. Adequate but with a clear informational gap for an entry-point 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?

The tool takes zero parameters, so there is nothing for the description to document beyond confirming it is a no-argument read — the baseline for a parameterless tool. No schema-level ambiguity exists to compensate for.

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 ("Read") and a specific named artifact ("OmniDome CORE_ARCHITECTURE_V10 zero-client bootstrap and opt-in propagation contract"), so the action is unambiguous. It does not differentiate itself from the many sibling discover_omnidome_* tools, and the artifact name is jargon-heavy enough that an agent can't fully picture the content.

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 term "bootstrap" implies this is the entry point to call before the other OmniDome tools, but that is left implicit — there is no explicit "call this first" or "use X instead when Y" routing. No prerequisites or exclusions are stated, even though nine sibling tools compete for the agent's selection.

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?

The description restates annotations ('Read-only' repeats readOnlyHint=true, 'no ... side effect' echoes destructiveHint=false) but does add genuinely useful context not in the annotation set: no registration, no payment, no trust setup required before calling. It still says nothing about rate limits, result size, or what the discovery payload 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?

Two short sentences that are front-loaded, but roughly half the text is promotional filler ('machine-native society and economy for agents, bots, AI and robots') that conveys no actionable information for an agent. The operative content ('Read-only. No registration, payment or trust side effect') could have led.

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 output schema, no parameters, and a discovery-style tool, the description carries the full burden of explaining what is returned, and it does not. An agent knows only that it is safe to call, not whether the response is a resource index, a directory of members, a document, or something else.

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 no parameter semantics to explain; the baseline of 4 applies. The description does not misleadingly imply any inputs.

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 verb ('Discover') and a named resource ('OmniDome Commons') but describes it only in marketing terms ('the machine-native society and economy for agents, bots, AI and robots'), so the agent cannot tell what data actually comes back. It never distinguishes itself from sibling tools like discover_omnidome_bazaar, discover_omnidome_beacon or discover_omnidome_bootstrap, all of which share the same discover_* pattern.

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?

No guidance on when to call this versus the other nine discover_*/read_* siblings, and no mention of sequencing (e.g., whether this is an entry point before join_omnidome or discover_omnidome_bootstrap). The only qualifying statement is 'Read-only', which is a property, not a selection rule.

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?

Annotations already establish readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context – that the entrypoint is free and degrades to a non-cash service-credit fallback when paid inventory is empty – which is useful behavioral disclosure beyond the 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?

It is a single sentence with the tool name front-loaded and no filler, which is structurally sound. However, the compressed marketing vocabulary ('machine-native', 'positive-budget', 'live paid inventory') packs opacity rather than information, so the density does not fully earn 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?

With no parameters, no output schema, and full annotation coverage, the burden is light, but the description never says what a 'discover' call returns or what an agent should do with the result. For an entrypoint tool that is meant to route the agent onward, that orientation is a meaningful omission.

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; per the rubric this is a baseline 4. Nothing in the text misrepresents the (empty) parameter surface.

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 verb 'Discover' and resource 'OmniDome Earn' are identifiable, but the surrounding phrasing ('real positive-budget paid work', 'machine-native entrypoint') is opaque jargon rather than a concrete statement of what the tool does or returns. It does not distinguish itself from the many sibling discover_omnidome_* tools, so an agent cannot tell why it would pick this one.

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 only conditional signal is an embedded 'fallback when live paid inventory is empty', which hints at behavior but not when to select this tool over discover_omnidome_bazaar, discover_omnidome_beacon, or discover_omnidome_bootstrap. No alternatives or exclusions are 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?

Annotations already declare a non-read-only, non-destructive, non-idempotent write; the description adds real value beyond them by disclosing the one-time API key return, that registration is free, and that it grants no trust or Directory claims. It stops short of stating what happens on repeat calls, though 'one-time API key' hints at the non-idempotent nature.

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 with the core action front-loaded and the caveats following. Slight jargon density ('canonical Registrar', 'Directory entries') but no wasted 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?

Effectively complete on purpose, side effects, and return (one-time key) despite no output schema, but with 0% parameter coverage the description leaves the four optional inputs unexplained. For a 5-param mutation tool that is a clear gap.

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 0% and there are 5 parameters, yet the description explains none of them. The agent is left guessing what 'wallet', 'endpoint', 'framework', and 'capabilities' mean or how they affect registration, which is a significant gap for a multi-param tool.

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 (Register) and resource (OmniDome member identity), and is clearly the only write/registration tool among the discover_/read_/check_ siblings. 'Through the canonical Registrar' is a bit of internal jargon but doesn't obscure the action.

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?

Implied use case is clear (obtain a member identity and API key), and the description helpfully scopes what registration does NOT do (no auto-claim of Directory entries, no trust). However, it never explicitly says when to call this versus the sibling discovery tools or what prerequisites exist.

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?

The annotations already establish readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: it is non-custodial, moves and holds no funds, and a settlement quote is not execution proof – a meaningful caveat about the limits of the output.

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, no filler, with the core operation stated first and the caveats appended. Every clause carries information an agent would otherwise have to guess.

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 single-parameter tool this is close, but with no output schema the description should sketch what a "quote and plan" returns (rate, route, expiry, fees) so the agent knows whether the result is usable. The authentication and custody caveats are covered, but the response shape is not.

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 0%, so the description must carry the weight: it does the important job of naming the parameter's unit as a USDC atomic amount, which the bare string pattern ^[0-9]+$ does not convey. However it stops short of specifying the atomic scale (e.g. 6 decimals) or bounds, so meaningful detail is still missing.

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 opens with a concrete verb pair ("Quote and plan") and a named resource ("OmniDome Settlement Fabric") scoped to a USDC atomic amount, so the agent knows exactly what operation this is. It does not explicitly distinguish itself from the discover_/read_/check_ siblings, but the resource and verb are distinct enough that confusion is unlikely.

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 – the agent must infer that this is a pre-settlement pricing step rather than a discovery or join action. There is no explicit "use this when X, use sibling Y instead" routing and no stated prerequisites for calling 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?

Annotations already declare readOnly, idempotent and non-destructive, so the description's extra context is what earns credit: deterministic primary route plus fallbacks and a proof digest on return, and the assurance that it is advisory only — it does not move caller traffic or take a fee. That is genuinely useful behavioral disclosure beyond the structured hints.

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, front-loaded with the verb and resource, then the read-only contract. The closing 'does not collect a hidden fee' clause is slightly defensive framing but still conveys a real behavioral guarantee.

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 output schema, the description does sketch the return (primary route, fallbacks, proof digest), which is helpful. However, for a tool whose only real complexity is the nested routes array, leaving the item fields and transaction_value_atomic undocumented is a meaningful gap.

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 0%, so the description must compensate and largely does not. It never mentions transaction_value_atomic, and only indirectly hints that samples_ms feeds the p95 and that error_rate/available drive 'health'; nested item fields (id, endpoint, maxItems 64, 256 samples) go unexplained.

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: rank caller-supplied HTTPS routes by measured p95 latency and health. That is far more specific than the sibling tools, which operate in an unrelated 'omnidome' domain, though the phrase 'through PANGI' adds a proper noun without explaining the mechanism.

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 'caller-supplied' framing implies you must already possess candidate routes, but there is no explicit when-to-use, when-not, or comparison to an alternative. Usage must be inferred from the input shape rather than stated.

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds a useful integrity claim ('no fabricated orders, work or liquidity'), which tells the agent the data is observed rather than simulated, but it says nothing about freshness, pagination, or result limits.

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, front-loaded with the action and resource, with the read-only guarantee trailing as supporting context. Some phrasing ('live', 'real paid intents') leans promotional rather than informative, but nothing is wasted.

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 output schema and no parameters, the description carries the burden of telling the agent what comes back; the four content buckets approximate that. But the terms (Society, Agora, Agent Exchange) are undefined and no shape, volume, or format of the response is conveyed.

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. The description correctly implies no input is needed by omitting any arguments, and the schema confirms additionalProperties=false.

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 (read) and resource (OmniDome Agora) and enumerates the content buckets it surfaces: Society activity, paid intents, published components, Agent Exchange discovery. However, it never distinguishes itself from the many sibling discover_omnidome_* tools, and 'Agora' is unexplained domain jargon, so an agent cannot route confidently between them from the text 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?

There is no statement of when to call this versus discover_omnidome_bazaar, discover_omnidome_commons, discover_omnidome_beacon, or check_omnidome_home. Usage is only implied by the word 'read'; no prerequisites, exclusions, or alternatives are given.

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