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

Annotations already cover readOnly, idempotent and non-destructive behavior, so the bar is lower. The description adds real value beyond them: result ordering, the fact that only public projects are returned, and how pagination signals end-of-results via an absent nextCursor.

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?

Three sentences, front-loaded with what the tool returns, then filtering, then pagination mechanics. No filler; each sentence carries operational information.

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 read-only, fully schema-covered list tool with an output schema, this is complete: scope, ordering, filter and the cursor loop are all covered, and return-value shape is left to the output schema as intended.

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% with per-parameter descriptions, so the schema already documents lang, limit, cursor and status. The description adds the constraint that only one status may be supplied and reinforces that continuation must reuse the same arguments, which goes slightly beyond the schema text.

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 (list), resource (public GMM-tracked projects), the fields returned (status, value, employer, contractor) and the ordering (newest first). An agent can distinguish this listing tool from single-item get_project and from the other list_* siblings without opening a 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?

Explains when to use the status filter (optionally one status, with example values) and precisely how to page (re-call with same arguments plus nextCursor). It gives clear context but does not name alternatives such as get_project or a search tool for narrow lookups.

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