LLM-generated session summary

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the bar is lower. The description still adds real value by disclosing the degradation path ('falls back to the session description if no summary has been generated yet') and the ingest step needed to populate summaries — non-obvious behavior an agent should know before trusting the output.

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 tight sentences, front-loaded with the return payload, followed by the fallback condition and the population command. No filler or restatement of the name.

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?

With no output schema, the description enumerates the returned fields and explains the fallback shape, which is exactly what an agent needs. Two parameters, one required, both documented in the schema; 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 100%, including the session_id format example and the enum for format, so the schema does the heavy lifting. The description adds no parameter-level detail (e.g., what the format enum changes in the response), so baseline 3 applies.

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 ('Returns the AI-generated structured summary for a WWDC session') and enumerates the payload (overview, key APIs, topics, code patterns, difficulty level). This clearly separates it from wwdc_get_session, which returns the raw session record rather than the derived summary.

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 only implied: the mention of a fallback to the session description hints at what happens when data is absent, and the ingest command hints at population prerequisites. There is no explicit statement of when to pick this over wwdc_get_session or wwdc_session_transcript_full.

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