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

The annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false, so the safety profile is partly known. The description adds useful behavior beyond annotations: it discloses that fork and renew accept idempotency keys in the body or Idempotency-Key header, and it separates draft reads from mutating POSTs. It does not disclose auth requirements (agent_key), the side effects of watch_update or renew, or what download returns, so it is adequate but incomplete.

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 action list and then uses a compact action:endpoint mapping that is dense but scannable. Every sentence carries routing or body information; there is no filler. It is appropriately sized given the nine supported actions.

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 high-complexity multi-action tool with 11 parameters, 9% schema coverage, no output schema, and only partial annotations, the description is missing critical context: the role of agent_key and other auth-related parameters, what the UUID parameters (id, wanted_id, transfer_id) are for, and what any action returns. It provides routing but not enough for an agent to invoke every action correctly without guessing.

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 only 9% across 11 parameters, so the description must compensate and it partially does: it documents body fields for fork (title, description, category, amount_usd), the 'enabled' body for watch_update, the idempotency_key for renew, and optional amount_usd. However, it leaves several prominent parameters undocumented (id, handle, agent_key, wanted_id, transfer_id, delete_credential, payment_signature), so meaningful gaps remain.

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 opens with a specific set of verbs (read, recheck, watch, renew, fork, download) applied to a clearly named resource, 'saved output passport', and then maps each action to its endpoint. This distinguishes it from siblings, none of which share the passport resource. It loses a point only because 'passport' itself is never explained, leaving the concept dependent on ecosystem knowledge.

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?

The enumeration of actions gives implicit guidance about what can be done, and the draft-vs-commit naming (fork_draft vs fork, renewal_draft vs renew) hints at a two-step pattern. However, there is no explicit statement of when to choose recheck instead of read, when renewal is appropriate, or what prerequisites exist (e.g., agent_key). Usage is implied rather than guided.

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