workspace.query

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the description's extra context is valuable. It adds that views are 'deterministic', warns that staleness is 'a paper-like warning, not a mathematical conclusion', and notes that retrieval preserves UNVERIFIED status. These are meaningful behavioral caveats beyond the annotations.

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?

Four concise sentences, each adding distinct value: the direct instruction, the main action, a parameter constraint, and two behavioral cautions. The description is front-loaded with the action and avoids redundant phrasing.

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 six parameters, no output schema, and good annotations, the description covers the essential functionality, the special CONTEXT requirement, and the staleness/verification caveats. It doesn't describe the return format, but given the simple view-enum nature and the annotations, it is reasonably complete for invoking the tool correctly.

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 schema covers most parameters with types and patterns, and only revision_id has a description in the schema. The tool description compensates partially by explaining target_card_id's role in CONTEXT and the explicit-link semantics. It doesn't elaborate on limit or IDs, but they are relatively self-explanatory given 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 clearly states the verb 'Read' and specifies the resource: 'RESUME, FRONTIER, ATTEMPTS, CONTEXT, or STALE' views from workspace state. It also distinguishes from capability.describe with the direct instruction 'do not call capability.describe', though it doesn't contrast with workspace.open/write.

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?

It gives a clear negative directive ('do not call capability.describe') and a parameter-specific requirement ('CONTEXT requires target_card_id'). However, it lacks explicit guidance on when to use workspace.query over sibling tools like workspace.open or workspace.write, leaving the selection somewhat open.

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