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

Annotations already declare readOnly, idempotent and non-destructive, but the description adds real behavioral context: it requires the artifacts:read scope, it filters to explicitly converged/usable results with matching simulation settings and valid constraints, and it leaves missing metrics as unknown rather than imputing. That is meaningful disclosure about what actually enters the Pareto set.

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?

Five short sentences, front-loaded with the core action and prerequisites before the constraint and workflow guidance. Dense but nearly every clause carries information; the phrasing 'to this brief' is the only noticeably awkward wording.

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?

An output schema exists and annotations cover the safety profile, so the description need only justify invocation and inputs. It handles the invocation reasoning and the convergence/constraint rules well, but with 0% parameter coverage and an unusual nested evidence structure, an agent still lacks enough to confidently populate the candidates array.

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 0% for three required parameters, so the description carries the burden and mostly does not: project_id and brief_id are never explained, and the candidates array (1-16 items, each pairing geometry_job_id with simulation_summary_artifact_id) is only obliquely evoked by 'CFD summaries linked through mesh and geometry'. The 'matching simulation settings' clause hints at why paired evidence is required, but structure and constraints like the 16-item cap are undocumented.

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: comparing successful CFD summaries tied to a brief and reducing them to a Pareto set. It is clearly distinct from plan_cold_plate, which it names as the downstream consumer, though the phrase 'linked through mesh and geometry to this brief' is dense and takes a second read.

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 downstream guidance — use a feasible candidate as the baseline for the next plan_cold_plate grid and never declare a finite study globally optimal — which implies this runs after simulations converge. It does not say when to call it versus inspecting artifacts directly (get_artifact) or reviewing the brief, so the selection boundary is only implied.

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