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

Annotations already establish read-only/idempotent/no-side-effects, yet the description adds genuinely useful behavior: exactly what is redacted (no transcript, no recording reference, no rubric rationale) and the minimal permission scope required (simulation_suites:read). 'Read-only' repeats the annotation, but the redaction and permission disclosures go well beyond it.

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?

Opens with the core purpose and output shape, then the permission/CI rationale, then a terse safety note. Tightly constructed with little waste, though the CI-gating explanation is somewhat elaborate relative to the rest.

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?

No output schema exists, so the description carries the return-value burden and does so well, enumerating the projected fields and what is withheld. The remaining gap is parameter-level guidance (pagination, cursor), which is left undocumented.

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 only 20% (only organization_id documented), so the description is expected to compensate, and it does not -- limit, cursor, run_id and agent_id semantics are unaddressed. 'The same run' faintly implies run_id/agent_id identify the run, but pagination and cursor behavior are never explained.

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 resource (a simulation run) and a precise output shape (redacted pass/fail projection: per-case status, error codes, failed assertions, evidence kind). The phrase 'The same run as a redacted... projection' implicitly distinguishes it from the fuller run sibling, but does not name get_simulation_run directly, so sibling differentiation is only implied.

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 a clear use context -- a build server / CI job gating a deploy -- which explains when this narrow projection is preferable. It stops short of explicitly naming the alternative (get_simulation_run for the full transcript-bearing view) or stating when-not to use it.

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