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

Going beyond the readOnly/idempotent annotations, it discloses that logs, prompts, and the full run record are omitted, and that the call 'does not spend credits' – useful cost context. It stops short of describing error conditions or response shape details beyond the field list, keeping it at 4.

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-loads the core action and scope, then the return fields, then the constraints and next-step routing. Every sentence carries distinct information with no redundancy.

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?

Though there is no output schema, the description enumerates the returned fields (id, status, outcome cause, timestamps, scenario/project ids, names, sessionId, reportUrl) and the omissions, so an agent knows exactly what it gets and how to proceed.

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 both parameters (limit range/default, projectId filter) are already fully documented. The description restates the limit range and the projectId omit-behavior, adding reinforcement but little genuinely new meaning, 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 ('List the signed-in user's recent runs') plus ordering ('newest first'), and scoping ('the signed-in user's'). It is clearly distinguishable from siblings like get_run, list_projects, and list_scenarios.

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?

Explicitly explains the projectId filter ('keep one project; omit it for...across that user's projects') and routes the agent onward: use get_run for bug reports/screenshot file names, then get_screenshot. Also states 'no further page,' preventing pagination attempts.

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