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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond that with genuinely new behavior: it discloses the run statuses (QUEUED/RUNNING/DONE/FAILED), the fallback rule that the newest finished run is also returned while a run is unfinished, the exact contents of the summary, and what includeResult expands into. It also preempts a likely misuse by noting runs are started elsewhere.

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?

Purpose and the newest-run behavior are front-loaded, and the dense middle covers return shape efficiently in one sentence each. It is a long description, but nearly every clause carries information an agent needs; only the parenthetical explanation of the plan date is mildly expendable.

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 carries the full burden of describing return values, and it does so thoroughly: statuses, the dual-run fallback, every summary field, and the includeResult payload. Combined with annotations covering safety, an agent has everything needed to call and interpret this tool.

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 67% (runId and includeResult documented, projectId bare). The description enriches the schema rather than repeating it: includeResult is expanded from 'Adds the whole stored result' into a concrete list (finish histogram and curve, milestone dates, task criticality, duration sensitivity), and runId's replace-the-newest semantics are restated as a behavioral rule.

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: 'Read the Monte Carlo schedule risk runs of a project,' and enumerates what comes back (P50/P80/P90, plan date chance, target date chance, sampled events). This is far more precise than a generic get, but it never names or contrasts a sibling tool such as analyze_project_risks or schedule_health_check, so an agent must infer differentiation from the resource alone.

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?

Clear context for use: it reads stored runs, and the closing sentence 'runs are started from the project Risks tab or the REST API' implicitly tells the agent this tool cannot start a run. It also explains the runId switch ('reads one run by id instead'). However, no explicit when-not condition or named alternative tool is given for cases where the agent wants a new run or a different risk view.

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