Tap

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

Annotations declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: the specific return structure (compensating for missing output schema), that timeout applies 'per tap', and that auto:true includes 'heal diagnostics (current_code, page_inspection)' for broken taps. Does not contradict annotations.

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?

Highly structured and front-loaded. Three dense sentences cover: (1) purpose and return value, (2) three specific usage scenarios, and (3) auto-heal behavior with downstream tool integration. Zero wasted words despite covering 5 parameters and complex workflows.

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?

Excellent completeness given no output schema exists: the description explicitly documents the return structure and per-tap return semantics. It also maps the integration points with sibling tools (tap.run, forge.save, forge.verify). Minor gap: could elaborate on what 'health contract' means, but sufficient for domain users.

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?

With 100% schema coverage, the baseline is 3. The description adds meaningful usage context beyond the schema: it explains the filtering pattern ('omit site/name to check all taps'), clarifies timeout is 'per tap', and details the behavioral implications of auto:true (collects diagnostics for forge workflow).

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 explicitly states the tool 'Run[s] health checks on taps' with a specific verb-resource pair. It clearly distinguishes itself from tap.run ('when tap.run fails') and forge.save ('post-save validation'), and documents the return structure {status, score, rows, issues[], error}.

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 three explicit numbered scenarios for when to use: (1) diagnostic entry point when tap.run fails, (2) post-save validation after forge.save, and (3) batch health audit. It also specifies the parameter pattern 'omit site/name to check all taps' and the downstream workflow using forge.verify + forge.save.

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