Tap

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

Adds valuable behavioral details beyond annotations: specifies it reads from forge.draft (state dependency), and crucially documents return values ('score, rows, and data preview') since no output schema exists. Aligns with readOnlyHint=true and openWorldHint=true 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?

Two dense sentences with zero waste. Front-loaded with the core action, followed immediately by the critical constraint (reads from draft) and return value disclosure. Every clause 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 the lack of output schema, the description performs essential work by disclosing the return structure (score, rows, preview). It sufficiently explains the 3 parameters and establishes the tool's relationship to the forge.draft sibling, making it complete for agent selection.

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?

Effectively compensates for schema gaps. The description implies the URL parameter is the live test target ('live on a URL') and clarifies the expression parameter is optional ('no need to pass expression'). Reinforces the schema's description of the description parameter through the example pattern.

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?

Excellent specificity: 'Test the draft tap's extraction logic live on a URL' provides a clear verb (test), resource (draft tap's extraction logic), and context (live on URL). It distinguishes itself from sibling tools by referencing forge.draft specifically.

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?

Provides solid usage context by stating 'Reads code from forge.draft — no need to pass expression,' which clarifies the primary workflow and implies when to use the expression override. However, it doesn't explicitly contrast with forge_inspect or forge_save for complete guidance.

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