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

The description carries real behavioral weight beyond the annotations: it explains that glm_peak_paused is an intentional cost gate rather than a fault, that it sets no pause columns, and that runs resume at glm_peak_resumes_at. It also reconciles the readOnlyHint=false annotation by disclosing that the ui_review block can mint a GitHub installation token and read a remote file, so the call is not a purely local read.

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 purpose in the first line, then layered nuance. Dense but each paragraph addresses a distinct concern (status fields, roadmap distinction, GLM pause semantics, side effects). Slightly long, but no filler sentences.

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?

Given an output schema exists, the enumerated return fields are somewhat redundant, but the interpretive guidance (glm_peak_paused not being a failure, the roadmap count distinction) and the side-effect warning make the definition complete for correct invocation. Only the parameter itself is under-described.

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?

Only one parameter (project_id) with 0% schema description coverage, but the description clearly frames it as the project being inspected and the return fields tie back to it. No format, identifier style, or lookup detail is added, so it does not go beyond what the obvious field name already conveys.

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?

Opens with a concrete, scannable statement of the resource and its scope ('Check how a project is doing: what is in flight, what shipped, what is stuck'), then enumerates exactly what is returned. An agent can distinguish it from siblings like list_roadmap or project_digest without opening the schema.

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?

Provides clear interpretive context on when to read which field (e.g. zero open_tasks does not mean an empty roadmap, use list_roadmap for queued items). It names a sibling and its role, but stops short of explicit when-to-use/when-not conditions relative to tools like project_digest or list_projects.

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