List Brain Dumps needing triage

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds meaningful context beyond that: tenant scoping, overdue-first ordering, and the set of lifecycle states returned. No return format details, but with annotations and stated ordering this is solid.

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 tight sentences with the resource and ordering front-loaded and the usage context following. Slightly undercut by the ambiguous inline state list that overlaps confusingly with the status enum.

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?

There is no output schema, so the description partially compensates by describing ordering and the states returned, and annotations cover the safety profile. However, with three parameters at 0% schema coverage and a status enum that conflicts with the prose states, an agent lacks enough to call this correctly with filters.

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 0%, so the description carries the load, yet it only says "agent_id required" and never explains limit (default 50, max 200) or the status enum. Worse, the states it lists (captured, triage_due, overdue, resolved) do not match the schema's status enum (proposed, voting, locked, parked, rejected), which could actively mislead an agent constructing a status filter.

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 and resource ("Returns tenant-scoped Brain Dumps") and specifies ordering (overdue first), which distinguishes it from siblings like brain_dump and triage_brain_dump. The list of lifecycle states is somewhat abstract but the overall purpose is clear.

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?

"Use on Continuous Improvement and heartbeat cycles so unresolved dumps cannot disappear behind newer work" gives a concrete usage context and rationale. It does not name exclusion cases or explicitly point to triage_brain_dump as the alternative for acting on a dump, so it falls short of a 5.

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