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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavioral context the annotations don't cover: counters are only final once status is completed, 'missing' usually means a silent block, and any -1 must never be reported as 0%. This directly prevents a serious downstream reporting error.

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, all dense and front-loaded: identity and ordering first, then what the counters mean, then the critical -1 caveat. No filler or repetition of the schema.

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 carry return-value semantics, and it does well by explaining the inbox/spam/promotions/missing counters and the -1 sentinel. It leaves the rest of the run object's fields (ids, dates, test association) and pagination unspecified, a modest 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%: both limit and testId are fully documented, including the default/max for limit and that testId comes from list_inbox_placement_tests. The description's 'optionally only those of one test' largely restates the schema, so the baseline 3 applies.

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 ('Lists inbox placement runs') plus meaningful scope and ordering ('newest first, optionally only those of one test'). This cleanly distinguishes it from the singular get_inbox_placement_run and from list_inbox_placement_run_results, which returns per-probe results rather than runs.

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?

The description implies when the optional testId filter is appropriate ('optionally only those of one test') but never states when to use this tool versus list_inbox_placement_tests or list_inbox_placement_run_results. Usage is inferable from the resource description rather than explicitly guided.

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