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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing concrete behavior: delivery as a notification and in each member's coach history, a 400-character cap, no links allowed, a rate limit of one note per brain per day, and an auth prerequisite of a connected account with an active coach plan owning the brain. These are exactly the operational facts an agent cannot infer from structured fields.

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 with the usage precondition front-loaded, then effect/limits, then account prerequisites. Dense but every clause carries information; the most useful constraint (one per brain per day) is buried at the end of sentence two rather than surfaced earlier.

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?

An output schema exists, so return values need no explanation, and the description covers the remaining burden for a 3-parameter mutation: trigger condition, audience, side effects, content limits, rate limit, and account/ownership prerequisites. Nothing an agent needs in order to call it 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 coverage is 67%, and the description meaningfully supplements it: it clarifies that text is sent verbatim ("as they are"), restates the 400-character ceiling, adds the undocumented 'no links' constraint, and reinforces that confirmation means the coach explicitly approved this exact note. Only brain_id gets no semantic elaboration beyond ownership in the prerequisites.

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: it sends a coach's note to every member training under one of their published coaching brains. It further specifies the delivery form (notification plus coach history), which no sibling tool does, so it is unambiguously distinguishable from the save_*/get_* siblings.

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 an explicit trigger condition: use it when a coach has written a note and clearly said to send it, and later that the account must own the brain on an active coach plan. It does not name alternative tools for related tasks (e.g. previewing or editing a note) or state when not to send, so it falls just short of full when/when-not guidance.

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