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

Adds substantial behavior beyond the annotations: it writes/persists findings, is idempotent through dedupe, returns the count of NEW risks inserted (0 when all already exist), and performs no LLM call or plan gate. The return-count disclosure is especially valuable given there is no output schema.

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-loaded with the action and destination, then a compact detection list, then idempotency/return behavior, then usage triggers. Every sentence carries distinct information with no repetition.

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 compensates by explaining what is returned (count of new risks). Combined with the detection rules, idempotency, and usage conditions, an agent has everything needed to invoke and interpret the call.

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?

Single parameter with 100% schema description coverage, so the schema already documents projectId fully. The description implies the scan target is a project but adds no format or syntax detail beyond the schema field. 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+resource ('Run deterministic schedule-risk detection on a project') and enumerates the exact detection rules (overruns, overdue tasks, >30% unassigned, stuck-at-99%). It also names where results go ('persist ... to the Risks tab'), so it is distinguishable from siblings like get_schedule_risk and analyze_project_risks.

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 clear triggering contexts ('Use after import or when the Risks tab is empty and the user asks ...') and rules out LLM-based/plan-gated alternatives via 'No LLM call, no plan gate'. It stops short of naming the specific sibling tools it is an alternative to (e.g., analyze_project_risks, compute_risk_patterns).

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