get_proof_token

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

Beyond readOnlyHint=true, the description discloses non-obvious behavior: the token is re-signed after a signing-key rotation and supersedes any older copy, every read is audited, revoked/expired returns proof_not_live while a suspended proof is still served, and the account's own verified assets return owner_session_required (not_found with a test key). These are exactly the surprises that would otherwise derail an agent.

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?

Scope and identifier form come first, then edge-case behavior, then the separate ACCESS note, so the structure is front-loaded and navigable. It is dense and a few clauses (the test-key parenthetical) could be trimmed, but nearly every sentence carries operational 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?

The tool is a single-parameter read with an output schema, so return-value shape needn't be re-explained; the description instead uses its space for access prerequisites and error semantics. Nothing an agent needs to call this correctly — auth, key scoping, error cases, alternatives — 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 the id parameter is already documented as ph_ctl_<32 hex>; the description largely restates the handle form. It does add real meaning about how the handle resolves: a sub-account-bound key reads only that sub-account's proofs, and another's handle answers not_found.

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 first sentence states a specific verb and resource ('Get the current token of a proof you own') plus the required identifier form (ph_ctl_* handle). It explicitly routes delegation handles (ph_dlg_*) to get_delegation_token/get_delegation, so an agent can separate it from the nearest sibling 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?

It names the alternative tools for delegation proofs and the condition that selects them, and calls out account access prerequisites (PROOF_API_KEY required; start_login does not unlock this tool). It also explains what to expect for revoked/expired versus suspended proofs, which is usage-relevant guidance rather than marketing.

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