Record a coaching event

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description doesn't need to restate mutation. It adds useful behavioral context: each call appends a new entry, the history is kept with the user's data export, no tool reads it back, and it does not replace saving facts through update_coach_profile or upsert_goal. It also discloses the return value ('Returns the stored event').

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 dense but well-organized: it front-loads the core action, then gives usage timing, exclusions, duplication warning, persistence context, and return value. Every sentence earns its place, though it is slightly long and could be tightened.

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 2-parameter tool with 100% schema coverage, an output schema, and annotations, the description covers everything an agent needs: what to record, when to call it, when not to, how to avoid duplicates, what the payload should contain, and what the tool returns. No critical gap remains.

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%, so the schema already documents both parameters. The description adds value by explaining the payload's purpose in context ('the gist, in the user's language') and giving concrete examples for goal_review and deload_advised/red_flag_raised, which goes beyond the schema's generic description.

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 uses a specific verb ('Append a dated milestone') and names the exact resource ('the user's coaching history'), then enumerates the concrete event types it records. It also explicitly distinguishes itself from siblings like log_session and upsert_goal, so an agent can tell them apart 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?

It gives explicit when-to-call guidance ('at the end of the step the coaching prompt names'), gives concrete examples (type='checkin' after a check-in), and names exclusions ('not for ordinary chat, logged workouts (log_session) or goal edits themselves (upsert_goal)'). It also warns against duplicate calls ('do not repeat one').

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