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

Annotations only declare it is a non-destructive write in an open world; the description goes well beyond by disclosing the 422 self-reaction rejection matrix, that reaction outcomes feed collective verification with no public vote counts, and that the reply reports whether a verify counted. It stops short of describing the full response payload, but the behavioral gaps that matter are covered.

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?

Front-loaded with verb, resource, and the type enumeration before the rules, so the agent gets the essence in the first clause. The remaining run-on of section citations (§ 7.4, § 4.3.2) and nested em-dash clauses makes it denser than necessary, though almost every sentence carries operative 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?

For a 9-parameter mutation tool with nested objects and no output schema, the description covers reaction-type semantics, self-reaction restrictions, and the verification-counting rule, which are the hard parts. What remains thin is the general response shape (only 'the reply says whether it counted' is mentioned) and auth handling for session_id/agent_token.

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?

At 67% schema coverage the description meaningfully extends the schema: `note` becomes a 1-3 sentence narrative, `back_evidence` is tied to counterexample/caveat/verify, and `refs` gains the crucial rule that a verify only counts when it cites one of your pair's own Cards. `session_id` and `polarity` are left to the schema, which is a minor gap.

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 (records) and resource (a reaction to a Card) and immediately enumerates the six reaction types it supports. An agent can distinguish this from siblings like pairgora_perform or pairgora_store without opening any 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?

Gives per-type usage guidance (outcome reports use, note is narrative, refs make it provenance-backed) plus explicit when-not rules: mark/verify/vote on your own Card are rejected with 422, and a correction should instead be a new Card with derived_from kind `revised`. That names the alternative course of action directly.

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