Query tasks

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context by stating 'Results are paginated and compact by default,' which agents must know to retrieve complete data, and it clarifies custom-perspective semantics.

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 carry the core purpose, pagination behavior, the primary alternative, and the main pitfall. Every sentence earns its place, and the most important information is front-loaded.

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 43-parameter read tool, the description cannot enumerate every filter, but the schema descriptions cover the parameters in detail and an output schema exists. The description supplies the high-level invocation behavior, pagination, the recommended alternative, and the key source=custom clarification, making it complete enough for safe use.

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 98%, so the baseline is 3. The description adds value beyond the schema by explaining that custom perspectives are saved views rather than tags, which is not obvious from the parameter list alone and helps agents choose between source=custom and tag-based filtering.

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 opens with 'Read tasks from Inbox, Flagged, Forecast, tags, projects, custom perspectives, or an ad-hoc filter,' naming the verb, the resource, and the supported sources. This goes well beyond the title 'Query tasks' and clearly separates it from sibling tools like count_tasks and query_projects.

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 explicitly directs agents to 'Use count_tasks when you only need totals,' naming the alternative and the condition that selects it. The note that 'Custom perspectives (source=custom) are saved views, not tags' also prevents a likely misuse of the tag parameters.

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