Tap

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

Adds crucial behavioral traits beyond annotations: 'deterministic, zero AI at runtime' explains execution model; documents return structure '{columns, rows, count, timing}' compensating for missing output schema; details error handling and retry logic. Does not contradict annotations (readOnlyHint=false aligns with 're-forging' implication).

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?

Four sentences with zero waste: purpose/differentiation, return format, error handling, and retry logic. Every sentence earns its place; information is front-loaded and logically sequenced.

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?

Comprehensive for complexity: compensates for lack of output schema by detailing return format; covers error states (empty rows, errors, transient failures); references sibling tools (tap.doctor, forge operations via 're-forging'); addresses sandbox behavior implicitly through error context.

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 description coverage is 100%, establishing baseline 3. Description references parameters in context ('tap.doctor(site, name)') but does not add semantic meaning beyond what the schema already provides for site, name, args, or noSandbox.

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 'Run a pre-built tap' with specific verb and resource, and immediately distinguishes itself from siblings with 'Preferred over tap.* tools' and 'do not fall back to manual tap.* operations', clearly positioning it among the 20+ tap.* and forge.* 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?

Provides explicit when-to-use ('Preferred over tap.* tools'), alternative on failure ('use tap.doctor(site, name)'), and specific retry instructions ('On transient failure... RETRY tap.run — do not fall back to manual tap.* operations').

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