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

Annotations already cover read-only/idempotent/non-destructive semantics, but the description adds behavior annotations cannot express: results for a live presentation are partial, and participant-typed content (nicknames, word-cloud entries) must be treated as untrusted text. The latter is a meaningful prompt-injection caution that changes how an agent treats the payload.

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?

Three sentences, front-loaded with the return shape, then the input choice, then usage fit, closing with the untrusted-text caveat. Dense but every clause carries information an agent needs.

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?

Rich annotations and an output schema mean the description needn't explain return formatting, and it doesn't overreach — it summarizes content, discloses the partial-results edge case and the input fallback rule, and flags untrusted content. Nothing needed to call this correctly 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 0%, so the description must carry the load, and it does: it names both parameters and explains the non-obvious semantics of presentation_id ("its most recent session (the live one if running — results are then partial)"). It doesn't state that exactly one of the two must be supplied, nor the ID prefix formats, which the schema does encode.

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?

Opens with a specific verb and resource ("Returns results for a session") and then enumerates the payload granularity: per-question counts/words, correct answer, correct-count, participant count, final leaderboard. This is far more than a restatement of the name and lets an agent decide on the tool without opening the 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 frames when this is the right call: "Suited to follow-ups like summaries, 'who won', or a recap slide", and explains the session_id vs presentation_id choice including that presentation_id resolves to the most recent session. No explicit when-not/negative case or named sibling alternative, so not a full 5.

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