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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the description doesn't need to restate safety. It adds real behavioral context beyond that: default sort order, the trimmed-column return shape, and the batch-scoped meaning of `reference` (`1-2` = work 2 of batch 1) — a non-obvious domain rule.

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?

Roughly four sentences, front-loaded with purpose, ordering and return shape before the parameter guidance. Dense but every clause carries information; the parenthetical on `reference` could arguably be trimmed, but it clarifies a genuinely confusing identifier.

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 correctly carries the return contract by enumerating the trimmed fields and showing the escape hatch (`get` with kind work). Ordering, scoping, filtering, and the reference format are all covered — nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so baseline is 3, but the description adds interaction semantics the schema can't: `query` searches across every reachable project unless `projectId` is supplied, in which case it searches inside that project. It also elaborates `status` and `reference` beyond the enum values.

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/find) and resource (Works), specifies the default ordering (newest-updated first) and the exact return projection (id, reference, title, size, status, batchId, projectId). It also distinguishes itself from the sibling `get` by pointing there for full detail, so an agent can route without opening either 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 the two usage modes clearly: pass projectId to scope to one project, and query searches titles/descriptions either globally or within that project. It names the alternative (`get` with kind work) for full detail. No explicit when-not-to-use case, which keeps it from a 5.

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