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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the description only needs to add context. It does add some: 'enrich an agent as its ERC-8004 owner (signed)' signals a signature/auth requirement, and 'pending — the protocol manifest approval queue' discloses an async review step. It still omits idempotency and conflict behavior for 'register' and says nothing about what a write actually changes.

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?

Two dense sentences that front-load purpose, then the sibling routing, then the action glossary — good ordering with no filler. Slightly eroded by a run-on first sentence and the vague phrase 'with what came back' for the inbox action.

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 36-parameter, five-action tool with nested objects and no output schema, the description does the minimum viable job of explaining each action. It never describes return shapes (e.g. inbox results, register outcome), pagination for the 'inbox' action despite a limit parameter, or error conditions, so an agent knows what to send but not what to expect.

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 every parameter is already tagged with its applicable action(s), so the schema carries the load and 3 is the baseline. The description's action summaries add operational meaning (signed enrich, https card URL, decoding contracts/events) but name almost no parameters directly, so it does not meaningfully extend the schema.

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 line and the action-by-action breakdown ('register — register an agent by the https URL of its own card; enrich — ...; inbox — ...') give a concrete verb+resource for each of the five modes and clearly frame the tool as the seller side. It also distinguishes itself from the buy path. It loses a point because the umbrella purpose ('Lists you as a seller') undersells a heterogeneous tool that also registers protocols and reads approval queues.

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?

'For buying use taifoon_find' is the only explicit routing rule, and it is genuinely useful. However, the tool overlaps heavily with siblings that go unnamed (taifoon_register for agent registration, taifoon_grade for manifest grading), and the description never says when to pick this tool's 'protocol' or 'pending' actions over those siblings. Usage is therefore implied by the action list rather than stated.

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