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 value beyond that by disclosing the result ordering ('newest first') and the shape of each result (its model and deployment status), which an agent would otherwise have to discover by calling.

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?

A single sentence front-loads the resource and scope, and every clause carries information (scope, ordering, returned fields). The nested parenthetical defining what a prompt is makes it denser than necessary, but nothing is padding.

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?

With only two optional parameters, no nested objects, and no output schema, the description supplies enough: what entity is returned, in what order, and which fields come back. The only modest gap is the absence of any hint about result volume or how the name query interacts with the listing.

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% for both parameters, so limit and query are already documented in the schema itself. The description adds no further parameter detail — it never mentions that filtering by name is possible, though 'newest first' implicitly confirms the fixed sort order is not parameterizable. Baseline 3 applies when parameter documentation is fully carried by the schema.

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 names the resource (workspace prompts), its scope ('single prompts', one model call with set messages), the ordering ('newest first'), and the fields returned (model, deployed). The parenthetical defining prompts as a distinct entity from workflows and agents helps separate it from sibling search tools, though the verb is only implied by the tool name rather than stated (e.g., 'list' or 'find').

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?

Usage is implied rather than stated: by defining prompts as 'the third kind of thing besides workflows and agents', the description helps an agent pick this over search_workflows or search_agents when the target entity is a prompt. There is no explicit when-to-use or when-not-to-use guidance, and no mention of how the optional name query changes behavior.

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