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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable specifics: 'read-only fixed-source output; writes no files and uses no network'. This reinforces and contextualizes the annotations, though it omits details about the 'format' parameter behavior.

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 only four sentences but contains an awkward 'Use: use after...' redundancy and an erroneous parameter list. It is compact, but the incorrect references and slight redundancy prevent a higher score.

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?

The description covers when to use, effects, and basic inputs, and the presence of an output schema removes the need to describe return values. However, it introduces non-existent parameters and fails to explain the 'format' parameter's role, leaving a complete understanding incomplete.

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 all three parameters (source, file, format), so baseline is 3. However, the description incorrectly mentions 'codes' and 'maxPasses' which do not exist in the schema, misleading an agent into passing non-existent parameters. It does correctly identify source as required, but the false parameter references are harmful.

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 states the tool 'Auto-fix mechanical Swift errors detected by axint.swift.validate', identifying a specific verb+resource and distinguishing it from the validator sibling. The purpose is unambiguous and actionable.

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?

Explicitly instructs to 'use after swift.validate when errors are mechanical' and to 'inspect remaining diagnostics manually'. This provides clear when and how to use, and what to do after, effectively differentiating it from the validation tool.

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