list_tasks

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

There are no annotations, so the description must carry the burden of disclosing behavioral traits. It implies a read-only list operation but doesn't explicitly confirm safety, output format, or potential side effects. Mentioning the wrapper adds minor implementation context but is insufficient.

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?

The description consists of two short sentences, front-loads the primary action, and contains no redundant text. It earns a perfect score for conciseness.

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 tool with no output schema and no annotations, the description should clarify return values and note all allowed kinds. It mentions only three of the four kinds and doesn't describe whether the output is a list or how prefix affects results. It's adequate for a simple listing tool but has clear gaps.

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 provides full descriptions for both parameters (kinds and prefix) with 100% coverage, so the description adds little value. It omits the 'tests' enum value from the parenthetical list, potentially confusing users, but does not contradict 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 identifies the tool's purpose as listing catalog entities (captures, materializations, collections) with a specific verb and resource. It distinguishes this from sibling task-specific tools like task_stats and task_logs. However, it omits the 'tests' kind that is allowed in the schema, creating a slight inconsistency.

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 description provides no guidance on when to use this tool versus alternatives like pull_specs or task_stats. It only states what it does and that it wraps a shell command, without contextual usage cues or exclusions.

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