Find Comparable Tasks

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

Annotations already declare read-only, open-world, idempotent, non-destructive. The description adds valuable behavioral context beyond annotations: it notes that cycle time is only computed for the top 12 comparables due to API cost, and it explains that similarity is computed from term overlap, tags, and section match. This helps the agent set expectations about performance and results. No contradictions found.

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 is three sentences, each with a distinct purpose: (1) state the tool's core function and value, (2) detail key return values and their significance, (3) explain similarity logic and provide usage guidance. No filler words, front-loaded with the most important information, and every sentence earns its place.

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?

Given there is no output schema, the description still discloses the key return values (story points and cycle time) and a practical limitation (top 12 cycle time computation). It also explains the similarity matching approach and the intended use case. This is complete enough for an agent to use the tool effectively without surprises, though it could have mentioned pagination or error conditions if applicable.

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 input schema has 100% coverage with descriptions for all three parameters. The description adds extra meaning by explaining that the 'task' parameter accepts multiple formats (name, URL, or GID) and by highlighting that 'limit' affects cycle-time computation due to API costs. This goes beyond the schema's literal field descriptions and helps the agent choose parameter values wisely.

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 states a specific verb ('Find') and resource ('completed tasks similar to a target task'), and immediately clarifies its purpose ('anchor an estimate on real history'). It also distinguishes itself from sibling tools by mentioning reference-class forecasting and the specific similarity criteria, making it clearly different from generic search or match tools.

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 explicitly tells when to use it: 'Use this before estimating' so the estimate is grounded in real costs. It provides clear context on what the tool returns and why it's valuable. It does not explicitly mention when not to use it or name alternatives, but the guidance is strong enough for an agent to decide appropriately.

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