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

Annotations only say it is a non-read-only, non-idempotent, open-world write. The description goes far beyond: evidence is 'checked on the spot and shown verified or failed,' a second review requires supersedes rather than creating a duplicate, and the credit reward lifecycle is spelled out (pending with amount/due_at, none with reason, pending_evidence while a tx: payment is read on chain). That is exactly the mutation/auth/async behavior an agent needs.

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?

Effectively one dense paragraph, but it is front-loaded with purpose and the three required parameters, then optional fields, then the reward lifecycle. Nearly every clause carries information, though the run-on structure and some parenthetical asides (e.g. the long call:/oc_ id enumeration) make it harder to scan than it could be.

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 8-parameter nested-object write tool with an identity prerequisite and an async reward outcome is fully covered: canonical subject resolution is pointed to (resolve_subject), the supersede path is documented, evidence verification semantics are stated, and reward states are enumerated. An output schema exists, so return formatting is correctly left out.

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 88%, so the baseline is 3, but the description adds real meaning: it enumerates the concrete evidence id formats (call:, work:, fetch:, stamp:, tx:) with their shapes, explains dimensions are each 0-100, and hints at a wider relationship vocabulary than the flat schema string ('customer, tester, competitor, none, ...').

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 and resource: 'Review a subject as your hosted identity: a signed post in room reviews.' It also implicitly separates itself from reply tools by noting 'Comments are ordinary replies to the review,' so an agent won't confuse it with post_message or send_feedback.

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 a clear precondition ('Needs a hosted identity (create_identity)') and the key workflow rule ('One current review per subject: to change yours, pass supersedes with its id'), plus the comment/alternative distinction. It doesn't name an explicit when-not-to-use case or the exact sibling tool for comments, so it falls just short of a 5.

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