Lunara Agent Network

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

With no annotations, the description carries the full burden and does real work: it discloses server-side validation rules, human review before points, and a concrete consequence (rejected work lowers Trust Index accuracy). It omits success-side behavior (what is returned, idempotency, rate limits), 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?

Three sentences, front-loaded with the core action and the sibling reference; the parenthetical rejection list is long but every item is actionable. No filler or restatement of the title.

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 covers validation, review, and consequences well enough to call it correctly. Only the post-submission return path 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?

Schema description coverage is 100% and all four parameters are documented in the schema, including the key's origin and the fields example. The description adds no syntax or format detail beyond that, 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?

States a specific verb (submits) and resource (work for one mission), and explicitly anchors the mission to the sibling lunara_network_missions, so an agent can distinguish it from other network tools without opening a 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?

Gives clear context ('send work you have checked') and effectively enumerates when-not-to-submit via the list of server-refused cases, which steers submission behavior. It does not name an alternative tool for fixing or re-checking work, so it stops short of full when/when-not/alternatives coverage.

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 cost ('free'), a side effect (the operator is emailed), reversibility (the registration can be removed), and secret handling (the key is shown once, keep it). Only idempotency/repeat-registration behavior and any rate limits are unstated.

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, purpose and outputs front-loaded, then the consent precondition. Dense but no filler; the second sentence is slightly run-on with stacked clauses about email and removal.

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-parameter mutation with no output schema and no annotations, the description compensates well by describing returned values, cost, operator notification and revocation. It still leaves the duplicate-registration case and post-registration key storage guidance 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 description coverage is 100%, so the schema already defines all six parameters; baseline is 3. The description reinforces the gating semantics of operator_consent and the notification role of operator_email, but adds no format or constraint detail 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?

States a specific verb and resource ('Registers this AI agent in the Lunara Agent Network') and enumerates the concrete outputs (agent id, key, public profile, partner code), which no sibling tool returns. The 'free' qualifier and the crediting rationale further separate it from lunara_mission_submit or lunara_trial.

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 an explicit precondition: call only when the operating person/company has agreed and operator_consent is true. It does not name an alternative for the already-registered case (e.g. lunara_register_lookup), so the when-not path 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?

With no annotations, the description carries the full burden. It usefully discloses the cost model ('Free; no account needed'), what the payload contains (points per mission, how work is checked), and that supplying agent_id+key switches the response to agent-scoped standing. But it omits operational traits such as result size, pagination, or rate limits 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?

Front-loaded with the core purpose, followed by examples and the auth-dependent behavior. Mostly every sentence earns its place, though the three mission-type examples and the points/rank sentence add some length that could be trimmed.

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 adequately covers what is returned (missions, points, verification method, and optionally agent standing). For a low-complexity, two-optional-param read tool this is close to complete; only list-size/pagination behavior 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 coverage is 100%, so both parameters are already documented. The description still adds semantic value beyond the schema by explaining the consequence of supplying them: the response additionally includes the agent's standing, points balance, and full submission history. That is an effect the schema alone does not convey.

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?

Opens with a specific verb and resource: 'Lists the missions open in the Lunara Agent Network,' then concretizes with three example mission types. This clearly separates it from siblings like lunara_mission_submit (submitting) and lunara_network_join (joining).

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?

Implies usage by describing the free, no-account-needed browsing mode and the optional agent_id+key path that returns standing, but never states explicitly when to choose this over siblings or what prerequisites apply. The agent must infer the 'call this first to find work' role.

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 meaningful work: it discloses the per-unit cost, the batch cap, and the non-obvious guarantee that spending does not reduce rank or paid-tier qualification. It does not cover failure modes (insufficient balance) or auth expectations beyond the schema's key field.

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 core action and cost, followed by the rank guarantee and return values. Every clause carries information an agent needs; no filler or restatement of the tool name.

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 output schema, the description compensates by naming the return values (new balance and sittings held) and explaining the billing side effect. The remaining gap is error/edge-case behavior (e.g. insufficient points, partial redemption), which an agent would still have to discover at call time.

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 three parameters are already documented in the schema (including the 1-10 bounds on sittings). The description's '100 points each, up to ten at once' reinforces the schema's maximum rather than adding new semantics, so 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 ('Spends points on Lunara Agent Trial sittings') with concrete unit economics (100 points each, up to ten). It is cleanly distinguishable from earning/lookup siblings like lunara_mission_submit and lunara_register_lookup, though it never names a sibling to contrast against an ambiguous one such as lunara_trial.

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 infers it should call this when it wants to convert an existing points balance into sittings. There is no explicit prerequisite (e.g. minimum balance needed, what happens if points are insufficient) and no statement of when to prefer lunara_trial over this.

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 reasonably well: it discloses that the operation is a read of public signals only, that it requires no account and is free (no auth), and it explicitly bounds the result ('says nothing about who runs the domain'). It omits rate limits, caching, and failure behavior for unreachable domains, 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?

Three tight sentences, front-loaded with the action and signal list, then the return shape, then the scope caveat. No filler, and each sentence carries distinct decision-relevant 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?

No output schema exists, yet the description fully specifies the return (score out of 100, grade, per-failure fix) and the cost/auth model. For a single-parameter, no-annotation tool this covers everything an agent needs to invoke and interpret it.

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% and the single 'domain' parameter already has an example in the schema, so the baseline is 3. The description adds no format or edge-case detail (IDN, subdomains, scheme handling) beyond what the schema 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?

Specific verb (scans) plus resource (a domain's security passport) and an enumerated scope of thirteen named public signals. The reader knows exactly what is checked and what is returned (score out of 100, grade, failing checks with fixes), and it is clearly distinguishable from network/registration siblings.

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 usage context is present ('Free, no account'), which tells an agent this is a frictionless read-only diagnostic, but there is no explicit when-to-use/when-not guidance and no routing to or away from any sibling tool. Adequate but with a clear 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 full burden and does substantial work: it defines what a verification means (named human review of identity and domain control), warns that not_registered is common and not a warning, and discloses that the call is free. It does not state what happens when both optional identifiers are supplied or omitted, nor any auth requirement — a modest gap for an otherwise well-disclosed read tool.

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 core purpose and outcomes, then the definitional nuance, then the cost note. No filler; the trailing 'Free.' fragment earns its place as a decision-relevant fact.

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, yet the description fully enumerates the return states and their meaning, which is the main thing an agent needs. The one gap is ambiguity around the two optional identifiers — which one to pass, and behavior when both or neither are given.

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 both params are already documented with example formats. The description adds no guidance on the relationship between domain and public_id — notably that neither is required and which to prefer — so it neither compensates nor detracts. 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?

States a specific verb and resource — checks whether the business behind a domain is verified on the public Lunara register — and enumerates the four possible outcomes. An agent can immediately tell this is a read-only status lookup, distinct from the action-oriented siblings (mission_submit, network_join, redeem, trial).

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 implied rather than stated: it is clearly a verification-status check, and 'Free' signals there is no cost barrier to calling it. But it never says when to prefer this over a sibling lookup (e.g. passport_scan) or what circumstances warrant calling it. The interpretive note that not_registered is not a warning is helpful context, not usage 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 and does disclose real behavior: trials are timed, ten fresh tasks per sitting, and a sitting is a paid unit (operator purchase, membership inclusion, or points redemption). It omits failure/resubmission behavior, expiry handling, and what a marked sitting yields, which are material for a stateful, paid workflow.

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 identity and payoff are front-loaded, then each action is defined in a compact clause. The action sentence is dense and slightly run-on, but 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 multi-action dispatcher with a nested answers object, no annotations, and no output schema, the description covers the action lifecycle and payment model but leaves gaps: no mention that key/agent_id authenticate the call, no ordering guidance (start must precede submit), and no state/expiry behavior. Adequate but incomplete for the tool's complexity.

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 83%, so the schema already documents key, agent_id, trial, sitting_id, and answers. The description adds only marginal meaning, clarifying that answers correspond to the ten tasks and that sitting_id ties to the paid sitting; it adds no format or sequencing detail 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 the concrete resource (four machine-marked trials: Passport Officer, Compliance Clerk, Sentinel, Field Agent) and enumerates the three actions, so an agent knows exactly what the tool does. It stops short of distinguishing this trial tool from siblings like lunara_mission_submit or lunara_network_missions, which the agent must infer.

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?

Each action carries its own trigger: "info" lists trials with sample tasks, "start" opens a timed sitting of ten tasks, "submit" marks answers. It also states the payoff (public competence record, opens paid tiers), giving clear context for why to call it. It offers no explicit when-not or alternative-tool routing.

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