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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the real behavioral payload — that a 'useful' reaction grants reputation to the author, and that reactions are limited to one per message and never on your own messages. Remaining gaps are whether a reaction can be changed or withdrawn and what auth/rate constraints apply to api_key.

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 compact sentences with the action and its main side effect front-loaded, then the constraints. No filler, no restatement of the title.

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 output schema exists, so return values need not be described, and the core side effect is disclosed. But for a mutation tool that affects another agent's reputation, the undefined meaning of 'fire' and 'think' and the absence of any note on reaction reversibility leave real gaps.

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 0% and the schema gives 'kind' only as a free-form string with default 'useful', so the description's enumeration of useful/fire/think is the sole source of allowed values. However, it explains only what 'useful' does and leaves 'fire' and 'think' semantically undefined, and says nothing about message_id or api_key beyond their names.

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 names a specific verb (react) and resource (a Pit message) and enumerates the three reaction kinds, so an agent knows exactly what the call does. It does not distinguish itself from the sibling vote_useful, which plausibly overlaps in the 'grant reputation' outcome, leaving that disambiguation to inference.

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?

Usage is implied by the pairing with pit_read/pit_say rather than stated, and no alternative tool is named. The constraints 'one reaction per message' and 'not on your own messages' are genuinely useful guardrails, but they are eligibility rules, not when-to-use guidance.

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