APIR Agent Verification

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

With no annotations, the description carries the full behavioral burden and does so well: it explains the narrowing invariant at every delegation hop, requires a human at the root, reports whether the grant is signed, and states that the answer is the mandate on file as of checked_at rather than proof of current permission. These are substantive behavioral traits beyond the 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 front-loaded with the core purpose and key invariant, and most sentences earn their place by adding trust-model semantics. It is slightly verbose in places, such as the emphasis that credential validity and mandate compliance 'are different questions,' but the length is largely justified for a complex authority-resolution tool.

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 one required parameter, no annotations, and no output schema, the description supplies the missing context an agent needs: what is resolved, how delegation chains work, what invariant is enforced, what the timestamp means, and the limitation that the result is recorded evidence rather than live proof. Nothing critical is absent for correct invocation and interpretation.

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 schema already explains that query accepts an agent name, credential id, or agent UUID. The description does not add format or syntax guidance for the query parameter, 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?

The description states a specific verb and resource: resolving the human mandate behind an AI agent, including actions permitted, value cap, expiry, signature status, and delegated chain. It also clarifies the key distinction from a sibling-like concern by noting that a valid credential may still be acting outside its mandate, which helps an agent separate this from verify_agent.

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 an explicit usage condition: 'Use this before letting an agent transact, sign, spend or commit on someone else's behalf.' It also warns about timing by saying to check again at the point of action, which is concrete when-to-use guidance rather than implied context.

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 delivers useful context: the key algorithm (Ed25519), the concrete publication locations (apir.ai/.well-known/jwks.json and did:web:apir.ai), and the rotation behavior that retired keys remain published for older credentials. It omits any caching, rate-limit, or availability notes, but the disclosed traits are genuinely beyond what a bare signature would convey.

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 each adds distinct information (purpose, trust rationale, publication formats, key-retention policy). No filler or restated title text.

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 signal the return shape — and it does, via the JWKS endpoint and did:web identifier. Combined with the absence of parameters, this covers what an agent needs to call the tool correctly, with only minor gaps around response/refresh mechanics.

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 and the schema is empty, so there is nothing for the description to disambiguate. The baseline for a parameterless tool 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 a specific verb and resource — returning the Ed25519 public keys APIR publishes — so an agent immediately knows what the tool fetches. It does not explicitly name or contrast with the siblings (check_authority, verify_agent), which perform verification rather than key retrieval, so differentiation is inferred rather than stated.

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?

"so a signature can be recomputed offline without trusting any APIR response" clearly implies the use case (offline/independent verification), but no when-not condition or explicit alternative is given. The relationship to sibling verify_agent, which likely performs verification for you, 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 and does so well: it discloses that the call is free, unauthenticated, and requires no account, and it defines what VERIFIED technically means (Ed25519 signature recomputes against apir.ai's published key, unexpired, unrevoked) versus what it does not guarantee (good behavior). The explicit warning against over-reading VERIFIED and NO_RECORD is exactly the kind of interpretation context annotations could never supply.

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 verb and resource, then the accepted inputs, then the verdict set, then the interpretation caveats. Every sentence adds decision-relevant information (verdict semantics, over-reading warning, cost/auth facts); nothing is 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?

No output schema exists, so the description takes on the job of documenting all seven possible verdicts and their meanings, which it does explicitly, including the counterintuitive NO_RECORD case. Combined with the auth/cost disclosure that substitutes for missing annotations, nothing an agent needs to call or interpret this tool 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?

Schema description coverage is 100% and the single 'query' parameter is already documented with the same accepted forms (agent name, credential id, UUID, domain, DID). The description restates that list without adding syntax, matching, or disambiguation rules, so the baseline 3 for a fully-documented schema 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 and resource ('check whether an AI agent carries a real, cryptographically signed credential') and enumerates the five accepted identifier forms. The scope is narrow enough that an agent can distinguish it from get_verification_keys (which supplies keys) and check_authority (which is about authority) without opening any 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 for when this tool applies (any claim an agent makes about itself needs verification) and explicitly frames NO_RECORD as an honest answer rather than a red flag. It does not name the sibling tools or state when not to use this one, so the routing guidance is strong but not complete.

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