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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), and the description adds real substance on top: a five-minute TTL, the signing algorithm, the exact claims to validate, and the caveat that the signature proves origin/integrity only. It doesn't mention failure modes or what happens when the evidence has expired or the key endpoint is unreachable, which keeps it below 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 what the tool returns before the verification recipe and the scope caveats. Dense but every sentence carries information; slightly jargon-heavy phrasing is the only cost.

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?

An output schema exists, so return values need no further explanation, and the annotations handle the safety profile. The behavioral picture (TTL, verification steps, limits of the signature) is well covered; the only material hole is input-parameter meaning, which is scored separately.

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% and the description never mentions agent_id or api_key. The claim list ("issuer, audience, subject and expiry") refers to JWS fields, not input parameters, so it does not compensate for the gap. With neither schema nor description explaining what agent_id selects or when api_key is needed, the parameter layer is effectively undocumented.

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 plus resource ("Get a five-minute Ed25519 signed presence observation") and names the cryptographic primitive, which clearly sets it apart from siblings like evidence_signing_keys or run_signed_diagnostic. It stops short of explicitly contrasting with those siblings, so an agent still has to infer which related tool fetches keys versus which mints the evidence.

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 operational context: verify the compact JWS against the trusted key endpoint, then check issuer/audience/subject/expiry. The closing line ("Not an identity, reachability or safety certificate") is a genuine when-not boundary. It does not name the sibling that supplies the trusted key endpoint, so the routing is implied rather than explicit.

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