lookup_far_clause

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

The description adds value beyond the annotations by specifying that the tool 'auto-resolves the latest available date' and 'returns parsed clean text with heading, paragraphs, and citations.' While the readOnlyHint and destructiveHint annotations are present, the description enriches the agent's understanding of the exact return format, which is helpful for setting expectations on output. It doesn't contradict the non-mutating nature of the tool, but misses a tiny bit of context on potential rate limits or errors for a truly perfect score.

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 extremely well-structured and efficient. It uses a clear hierarchy: a one-line summary, followed by a usage example, a brief note on scope, a list of common examples, and a return description. Every sentence teaches the agent something new without being verbose or redundant.

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?

For a lookup tool with a rich output schema, the description is complete. It covers what the tool does, how to use it, and what it returns. It correctly assumes the agent doesn't need to know about mutation or side effects given the read-only nature, and it provides just enough context to avoid conflating this with the 12 sibling tools. The presence of the output schema means it doesn't need to over-explain return values, striking the right balance.

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 0% schema description coverage, the description bears the full burden of explaining parameters. It does an excellent job with the key ones: 'section_id' is explained with examples, 'chapter' has full semantics described (default '1' for FAR, '2' for DFARS). However, the 'date' parameter is never explicitly mentioned. While the 'auto-resolves the latest available date' line hints at its purpose, the description doesn't name the parameter when explaining this feature, leaving a small gap.

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's purpose: to look up the current text of a FAR or DFARS clause. It provides concrete examples of section identifiers and identifies the tool name in the description, effectively distinguishing it from the many sibling tools like get_cfr_content or search_cfr. It's a specific, action-oriented verb ('look up') tied to a clear resource ('FAR or DFARS clause').

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 explains when to use this tool (to get clean, parsed text of a specific clause) and provides the key usage context: how to switch between FAR and DFARS with the 'chapter' parameter, and that it auto-resolves the latest date. It effectively communicates the main differentiation from siblings like search_cfr (search) or get_cfr_structure (structure), though it doesn't say 'use X instead', it's clear from the examples and the 'Convenience tool' label that this is for quick, direct lookups.

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