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

The description explicitly states 'Read-only: returns grouped counts without changing suggestions or documents,' which directly aligns with the readOnlyHint and destructiveHint annotations. It goes beyond the annotations by clarifying no mutations occur to suggestions or documents, providing excellent transparency.

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 two sentences long, front-loaded with the primary use case ('Use this when the user asks how many'), followed by behavior and optional filter. No redundant words or unnecessary details are present.

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?

For a simple counting tool, the description fully covers purpose, trigger conditions, behavior, and parameter semantics. The absence of an output schema is acceptable since the return type (grouped counts) is implied by the description, and no other context is needed to invoke 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?

The single parameter space_id is described as 'Optional Space filter' in the schema, and the tool description adds 'numeric' and 'filter by' context, making its type and purpose unambiguous. Full parameter coverage is achieved with additional clarifying detail.

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 clearly states the tool returns grouped counts of suggestions by status (pending, snoozed, done, etc.) and identifies the resource as Autopilot/repository-sync suggestions. It distinguishes itself from list-oriented siblings by emphasizing counts rather than detailed listings.

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 explicitly states when to use this tool: 'when the user asks how many' suggestions in various states. It also mentions the optional space_id filter, giving clear guidance on invocation conditions. While it doesn't name alternative tools, the condition is specific enough to avoid confusion with list-space-suggestions.

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