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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds useful context that results span work created in other assistants, but says nothing about ordering, pagination behavior of `limit`/`before`, or what a result contains.

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 short sentences, front-loaded with what is listed and the store scoping. No filler, though the two mode sentences read as compressed fragments rather than a coherent call pattern.

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 six-parameter list tool with no output schema and half the parameters undocumented, the description covers only the mode parameters. An agent still lacks guidance on pagination (`before`+`limit` interplay), which the schema's `query` note hints at but the description does not resolve.

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 50%; the description gives real meaning for `view: "needs_you"` and `query` (search over past work) that goes beyond enum values. It leaves `kind`, `limit`, `store`, and `before` undocumented in prose, with `before` bare in both schema and description.

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 — 'List Fudge work for this store' — and clarifies scope includes work started in Fudge or another assistant. However, it never distinguishes itself from siblings like read_work or stop_work, so an agent must infer the boundary.

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?

Offers implied usage through the two modes: `view: "needs_you"` for items awaiting the merchant and `query` for past work. There is no explicit when-to-use versus read_work guidance, nor when to omit `query`, so the routing signal is partial.

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