tasks_list

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

Discloses ordering ('newest first'), default exclusion of plan-step tasks, and the special behavior of id lookup (ignores project/status/plan, no session scope). Annotations already declare readOnlyHint, idempotentHint, destructiveHint; description adds valuable behavioral nuance without contradiction.

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 sentences with no wasted words. Each sentence conveys a distinct mode of operation. Main purpose is front-loaded. Efficient and clear.

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?

Covers all three invocation patterns and ordering, but doesn't mention result format, pagination, or limits. Given no output schema and moderate complexity, it is nearly complete; a minor gap keeps it from a 5.

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% with parameter descriptions. The description adds context beyond the schema: for id, explains it performs a direct lookup; for plan, explains it lists step tasks; and implies the default behavior when plan is absent. The ordering information is not tied to a parameter but adds value.

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?

Description clearly states it lists a project's tasks with optional filters, including plan-step tasks and single-task lookup by id. Verb 'list' plus resource 'tasks' plus specific behaviors (newest first, exclusion of plan-steps) distinguish it from sibling tools like tasks_add or tasks_update.

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?

Explicitly tells when to use default (non-plan tasks), when to pass plan (to list plan steps), and when to pass id (to load a single task ignoring project/status/plan). Also implies 'when not' by noting that id lookup ignores other parameters. Provides clear alternatives within the same tool's interface.

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