Collect a grill that was still running

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

Annotations already declare readOnlyHint and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: it blocks and waits up to 45 seconds if the job is still running, and it defaults to the latest grill when job_id is omitted. It does not say what happens on timeout or failure.

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 purpose, then conditions, then the constraint — good ordering and no filler. The enumeration of detail values duplicates the schema and could be trimmed.

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 two-param read tool, it covers the key behaviors an agent needs: the blocking wait, the latest-grill default, and the prohibition on writing layers. Without an output schema, a brief note on what is returned (or timeout behavior) would close the remaining gap.

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 100%, so the enum meanings and job_id fallback are already documented in the schema. The description largely restates the enum values and the job_id rule rather than adding new semantics. 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 ('collect a grill') and clarifies it retrieves a job that already returned an id, or a later layer of one. This distinguishes it from the 'grill' starter tool implicitly, though the jargon ('grill', 'layer') is domain-specific and the sibling grill_look_back is never mentioned.

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 conditional guidance: pass job_id when you have one, omit it to use the latest grill, and call detail deepen only when the person asks to deepen or go bigger. It also warns 'Do not write a layer yourself.' It stops short of pointing to grill or grill_look_back as alternatives, so the routing decision among siblings is incomplete.

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