Start assessment

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

Goes well beyond the annotations by disclosing credit consumption, a required permission scope (assessments:write), the dispatch of an asynchronous risk pipeline, and the returned fields. It complements destructiveHint=true with concrete cost/auth context rather than contradicting 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?

Four compact sentences that front-load the action, then cost, then permission, then return shape. Every sentence carries distinct, actionable information with no filler.

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 supplies the key return fields (assessmentPid, reportUrl) and an operational instruction about surfacing the link. Adequate for a 3-required-param mutation, though the unexplained projectPid is a small gap.

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% and artifactPids already points to air_list_artifacts with a max of 5. The description adds no meaning to the parameters, and projectPid remains undocumented in both schema and description, so this sits at the baseline.

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: 'Start a risk assessment on a project.' It is clear what the tool does, though it does not explicitly differentiate itself from close siblings like air_create_assessment_draft or air_run_full_assessment_pipeline.

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?

The description implies when to use it (you want to kick off a risk assessment run) but gives no explicit when-not or comparison to the alternative entry points in the sibling set. The agent must infer selection from the operation name alone.

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