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

Goes well beyond the annotations: states the call is free and never spends credits, that a human reads every message, that there is no reply to the agent and no promised fix, and that reproduced wrong results grant 10 free credits. These are non-obvious behavioral and incentive facts an agent cannot infer from the write-ish annotation profile.

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 purpose, then triggers, then constraints; nearly every sentence carries an actionable rule (credit cost, no promise of a fix, PII exclusion). The trigger sentence is dense and long, but it is not padding.

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 mutation tool with an output schema already covering the return value, the description supplies everything the agent still needs: when to fire, what to include, what to omit for privacy, cost implications, and the follow-up expectation. Nothing material is missing.

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 already 100%, so baseline is 3. The description adds real meaning: it pairs kind values with the user behavior that selects them, tells the agent to include contractId and the corrected value for wrong_result, and requires wouldPayUsd only when the user volunteered a price.

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 (sends a message to the people who build Prism) plus the return behavior (returns a confirmation). It is clearly not a contract-manipulation tool like prism_review_contract or prism_unlock_contract, so an agent can distinguish it from every sibling without opening a 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?

Explicitly enumerates trigger conditions mapped to each kind (wrong_result, missing, price) and gives an exclusion rule: 'Send it only when one of those happened, not after every result.' This is exactly the when/when-not guidance that routing decisions depend on.

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