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

Annotations only say the tool is not read-only, idempotent, and non-destructive; the description adds substantial non-structured behavior: the draft call saves nothing and returns the rules plus uncovered gaps, the save call validates against sample members and reports whether plans still work, and members train by the saved rules starting next session. Auth ownership requirements and the confirmation precondition are also disclosed, which is exactly the extra context annotations cannot carry.

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?

Front-loaded with the triggering condition, then the two call modes, then the account prerequisite and confirmation guardrail — a sensible order with little filler. It is dense and run-on in places, but nearly every clause conveys either a mode, a side effect, or a safety rule.

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 4-parameter, nested-object, non-idempotent-looking write tool, the description covers the trigger, both call modes, side effects, post-save verification, downstream member impact, and auth ownership. Return values are described even though an output schema exists, so nothing an agent needs to call it safely 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 100%, so the baseline is 3, but the description adds mode-dispatch meaning the schema cannot express: 'text' triggers the read-only draft path, 'rules' plus 'confirmation' triggers the save path, and text must come from the coach's words rather than being invented. The nested 'rules' payload (method, voice, banned_phrases, share) is only enumerated inside the schema description, not the function 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?

States a specific verb and resource: it reads a coach's own words into coaching-brain rules and can save them. The two-mode behavior (draft read-back vs. save) is spelled out, so the agent knows exactly what will happen. It never names the neighboring tools (start_my_coaching_brain, update_gym_brain, save_program_to_my_coaching_brain), so sibling differentiation is left implicit.

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 triggering condition with concrete examples: 'Use this when a Phorme coach describes how they coach...', and states the prerequisite (a connected Phorme account that owns the brain). It also constrains the risky path: set confirmation true only after the coach confirmed the read-back. It does not name when to prefer a different sibling tool instead.

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