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

Annotations already declare the write, idempotent, non-destructive profile, and the description adds real behavioural context beyond them: the call requires justification ('saying how you know'), it gates freezing the brief, and no default is ever assumed. It stops short of describing failure modes, what evidence must look like, or what the response contains.

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 tight sentences, front-loaded with the action, then the consequence, then the exclusion. 'It never gets a default' is slightly cryptic but not wasted; no filler.

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?

The output schema covers return values and annotations cover safety, so the main remaining burden is the undocumented parameters and the opaque vocabulary. For a four-required-parameter mutation with no schema documentation, the description leaves a meaningful gap an agent must bridge by trial.

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 description coverage is 0% and all four parameters (id, key, dimension, evidence) are bare strings. The description only obliquely implies the evidence parameter via 'saying how you know' and says nothing about id, key, or dimension, leaving an agent to guess what identifies a dependency and what values dimension accepts.

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 verb 'mark ... as settled' and the resource 'one thing the brief waits on' identify a state transition on a dependency, which maps to the tool name. The final clause separates it from later checkpoint work. The phrasing is metaphorical ('the brief waits on', 'settled', 'never gets a default') rather than plainly saying 'dependency', so an agent must interpret the domain vocabulary.

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 a clear trigger ('until it is settled the brief cannot be frozen') and an explicit exclusion ('later checkpoints ... are not settled here'), which steers the agent away from misuse. It does not name an alternative tool (e.g. grill_answer, grill_skip, grill_freeze), so routing between siblings still requires inference.

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