get_project_summary

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

With no annotations, the description carries the full burden, but 'get a project's counts' unambiguously indicates a read-only aggregation and 'cheaper than listing each' discloses a performance characteristic. It does not explicitly state side-effect-freeness or error behavior, but for a tool whose name and verb imply retrieval, this is adequate and adds value beyond the 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?

The description is four concise sentences. The purpose is front-loaded, followed by a cost rationale, a parameter note, and a resolution path. There is no redundant restating of schema fields, and every sentence earns its place.

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 single-parameter, read-only summary tool, the description covers the core purpose, when to use it, and how to obtain the necessary ID. It does not describe the exact return format, but it enumerates the counted entities, giving the agent enough context to interpret results. Minor gaps like error conditions or response structure are acceptable given the tool's simplicity.

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 100%, giving full parameter documentation, so baseline is 3. The description adds meaningful guidance on how to resolve a readable identifier to the required project_id via get_projects, which goes beyond the schema's simple type description and directly helps the agent prepare the parameter.

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 uses a specific verb ('get a project's counts') and enumerates the exact resources (work items, modules, cycles, states, members, pages, labels, intakes), making it clearly distinct from the many list/get siblings. It is not a tautology and immediately differentiates the tool as an aggregate summary rather than a detailed listing tool.

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 phrase 'Cheaper than listing each' explicitly states when to choose this tool over fetching individual lists, implying a when-not for detailed data needs. It also gives a concrete prerequisite step: if you only have a readable identifier, use get_projects to obtain the required project_id. This is direct, actionable guidance with an alternative named.

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