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

Annotations flag destructiveHint=true, which would be surprising for a chat tool; the description earns credit by explaining why ('The coach may adjust their workouts') and by noting the reply arrives in the same thread, implying conversation continuity. It does not mention non-idempotency (repeated calls post duplicate messages) or any rate/permission constraints, so it is not fully transparent.

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 short sentences with no filler: purpose and return value first, then usage triggers, then the side-effect caveat. Every sentence carries distinct information.

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 must cover the return, and it does ('returns the coach's reply'). It also warns about workout mutation via annotations being explained. Minor gaps: no guidance on formatting the message or what happens if 'today' is omitted, but nothing that blocks correct invocation.

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 50%: the 'today' parameter carries a detailed description with format and the pre-05:00 local-date rule, while 'message' is undocumented apart from its maxLength. The description only implicitly conveys what 'message' is and adds no constraint detail (e.g., what content the coach can act on), so the baseline 3 is appropriate.

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 their MONS coach'), plus the thread and return behavior ('in the same thread as the app, and returns the coach's reply'). No sibling tool does anything comparable, so it is trivially distinguishable from about_mons, check_readiness, or today.

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?

Gives explicit trigger examples ('any training question: soreness, a missed session, how a session should feel'), which is clear positive guidance. It stops short of naming when NOT to use it (e.g., for app/account questions that belong to my_profile or about_mons), so it falls short of a 5.

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