list_reissued_proofs

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

Annotations only assert readOnlyHint=true; the description goes well beyond that by disclosing that items are references rather than tokens, giving the reference shape {proof_id, reissued_at, token_url}, specifying oldest-first ordering, and noting that a sub-account-bound key sees only that sub-account's proofs. The access block also spells out the PROOF_API_KEY requirement and the need to restart the server, which is the kind of operational behavior an agent cannot infer from 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 front-loaded with the core action, then proceeds to result shape, sibling handoffs, scope exclusions, and access requirements. It is dense but each sentence carries operational value; the access paragraph is slightly long but necessary for a tool that fails without the right account.

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 read-only list tool with three params, a full output schema, and existing annotations, the description covers the remaining unknowns: what the returned references mean, how to exchange them for tokens, which proofs are out of scope, and what credentials are required. Nothing an agent needs in order to call and interpret this tool 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 schema already documents 'page', 'limit', and 'since' with an ISO-8601 example. The description still adds meaning beyond the schema by clarifying the inclusive lower bound ('at or after an instant') and the result ordering ('oldest first'), which affects how a caller interprets 'since' relative to pagination.

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 opening clause names the exact verb, resource, and filter: 'List your proofs whose token was re-signed at or after an instant, oldest first.' The reader immediately knows this is a filtered read over reissued proofs, not a token-fetch or revocation list, and the ordering guarantee is stated up front.

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 concrete triggering scenario — re-fetching after a signing-key rotation or a missed webhook — and routes the agent to the follow-up tools by prefix (get_proof_token for ph_ctl_*, get_delegation_token for ph_dlg_*). It also states an exclusion: proofs for the account's own verified assets are not listed here, plus an access prerequisite and an explicit negative ('start_login does NOT open this tool').

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