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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, so the description adds value by detailing return fields and truncation limits (max 10 wrong words, first 20 timeline events). This provides behavioral context beyond the annotations.

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?

The description is well-structured with front-loaded use case, followed by parameter guidance, return fields, and an agent instruction. It is slightly verbose but every sentence adds value. Could be more concise, but no fluff.

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?

Despite lacking an output schema, the description fully explains the return value (title, accuracy %, wrong_words up to 10, timeline up to 20 events) and provides an instruction to the agent to cite specific fields. This is complete for the tool's simplicity.

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 coverage is 100%, but the description adds meaning by explaining how to obtain session_id (from get_recent_session_results or picker chip) and that include_timeline defaults to true. This enriches the parameter semantics beyond the schema descriptions.

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 clearly states the tool returns session details (title, accuracy, wrong words, timeline) and specifies the exact user queries it addresses ('what did I miss', 'which words tripped me up', 'accuracy on session X'). It also distinguishes from siblings by focusing on a single session, referencing get_recent_session_results as the source for session_id.

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?

The description explicitly tells when to use this tool (user asking about session specifics) and how to obtain the session_id (from get_recent_session_results or picker chip). It does not explicitly exclude alternatives like get_session_trends, but the context is clear enough for an agent to decide.

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