graph_assessment

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds a genuinely non-obvious output-semantics guarantee — coverage is declared explicitly per domain and NOT_EVALUATED is never collapsed to zero — which is a behavioral trait the annotations cannot express.

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 its basis in the capability registry, followed by the scope enumeration and the NOT_EVALUATED caveat. Three short blocks, no filler; the only looseness is that the scope list could have been folded into the first sentence.

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 some burden for return semantics, and it handles the coverage-labeling rule well. But it is silent on 'limit'/pagination behavior and offers no routing versus the overlapping run_*_assessment siblings, so an agent still has gaps before invoking it correctly.

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%, so the description must compensate. It does so for 'scope' by enumerating the five accepted values (identity, directory, privileged, workload, azure), which the schema does not declare as an enum. However, 'limit' (default 200) receives no explanation at all, leaving half the parameters 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 ('Executa assessment de identidade') and names the mechanism ('capability registry') plus what it produces (per-domain EVALUATED/PARTIAL/NOT_EVALUATED coverage). It stops short of distinguishing itself from close siblings such as run_iam_assessment, run_enterprise_identity_audit, and run_agent_assessment, which an agent would need help telling apart.

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 only lists the accepted 'scope' values. It gives no when-to-use context, no prerequisites, and never names an alternative, even though the sibling set contains three other 'run_*_assessment' tools that overlap heavily in purpose.

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