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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior; the description adds the important non-obvious traits that it reads no store and that status remains pending until a discovery pass. That is real value beyond the structured metadata, though pagination and return-shape behavior are not covered.

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?

Two sentences, front-loaded with the resource and followed by provenance and status. The parenthetical source list is dense but every clause contributes to the workspace-only scope.

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 one-parameter, read-only list tool with rich annotations and full schema coverage, the description supplies the key caveat: no store read and pending status. It does not describe the opportunity fields returned, which is a modest gap because no output schema exists.

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 single application_id parameter is fully documented at 100% schema coverage, so the schema carries parameter meaning. The description's 'for one application' aligns with it but adds no syntax or constraint detail beyond 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?

It names the resource (keyword opportunities for one application) and its data provenance, so the agent knows this is a workspace-only read rather than a store query. It does not explicitly name a sibling as the alternative, so it stops short of full sibling differentiation.

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 'Reads no store' and 'pending until a discovery pass has completed' notes imply when the tool is useful, but the description never states 'use this instead of discover_keywords' or any other explicit alternative or exclusion. Usage is inferable rather than stated.

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