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

Beyond the readOnlyHint annotation, the description discloses substantive behavior: only live moves are returned by default, drafted body text is absent, has_draft acts as a marker, and include_resolved/since change what is returned. The explicit 'Read-only' statement reinforces the non-destructive nature and there is no annotation contradiction.

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 definition is dense but each sentence carries useful information, from the field list to the get_move handoff and the include_resolved/since guidance. It is not as tight as a two-sentence definition, but the length is justified by the number of behavioral details the caller needs.

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 there is no output schema, the description compensates by enumerating the output fields and key semantics (live only, no body, postures, has_draft, retrieval via get_move). The only unstated details are generic concerns like pagination and auth, which do not block correct selection or invocation.

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 schema already documents all three parameters at 100% coverage, so the baseline is 3. The description adds context beyond the schema by explaining the practical meaning of live-only by default, the reason to pass since while a deep scan fills the board, and the relationship between has_draft and the absence of bodies.

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 identifies the resource as the ranked growth-marketing backlog and enumerates included fields (title, why, area, status, rank, has_draft, posture), so an agent knows exactly what list_feed returns. It also distinguishes itself from the sibling get_move by stating that drafted bodies are not included and that get_move is the route to the working one.

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 tells the agent when to use it ('Read it before improvising growth work of your own'), when to use an alternative ('call get_move for the one you are working on'), and how to adjust behavior with include_resolved and since. This is direct, actionable guidance with no need for inference.

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