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

The description explicitly calls itself 'read-only' and says it 'remains available,' but the annotations set readOnlyHint to false, implying it may modify state. This is a direct contradiction between the description and the structured annotation, which is a serious inconsistency for an agent deciding safety.

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?

The description is front-loaded with purpose, then groups behavioral caveats and parameter details in separate sentences. Every sentence provides distinct, necessary 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?

Despite the contradiction, the description is impressively complete: it explains grouping by evidence class, absence of totals, that empty groups do not prove controls, that disclaimer_md must reach the user, and the effects of include_all. Since an output schema exists, it need not describe return values.

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?

With 0% schema description coverage, the description carries the full burden and delivers: it explains that limit defaults to 25 with a max of 100 and that include_all broadens the result set to resolved, dismissed, and out-of-scope records. This adds meaning the schema lacks.

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?

The description opens with 'Read a project's security-control observations and review boundaries,' which names a specific verb and resource. It clearly differentiates from the sibling tool 'run_control_gap_review' by emphasizing this is a read operation, and the 'read-only' statement reinforces the separation.

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?

It provides practical context: the tool is read-only, has no compute quota, and remains available after the trigger closes. This implies when to use it, but it never explicitly contrasts it with alternatives like 'run_control_gap_review' or states when not to use it.

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