nist-mcp

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

The description adds valuable behavioral context beyond the readOnlyHint annotation. It discloses that 'Results are cached locally' (performance characteristic), handles multiple file formats (PDF, XLSX, etc.), and explains how different parameter combinations affect output (table of contents vs. sections vs. pages). While annotations indicate it's not read-only, the description doesn't contradict this but adds practical implementation details.

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 efficiently structured with two paragraphs: the first explains core functionality and parameter behavior, the second provides usage context and optimization advice. Every sentence adds value - no redundant information or filler. The front-loaded first sentence immediately communicates the tool's primary purpose.

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 tool has an output schema (so return values are documented elsewhere), 100% schema coverage, and annotations covering the read/write aspect, the description provides excellent contextual completeness. It covers what the tool does, how parameters affect behavior, supported formats, caching behavior, and practical usage advice for large documents - everything needed to understand when and how to use this tool effectively.

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 description coverage, the baseline is 3. The description adds some semantic context by explaining how parameters interact ('Without section/pages, returns table of contents. With section, returns that section. With pages, returns those pages') and provides a concrete example for pages ('e.g., 1-50'), but doesn't significantly expand beyond what the schema already documents about each parameter's purpose.

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 retrieves publication content as Markdown, specifies the resource (NIST documents), and distinguishes it from siblings like download_document (which likely downloads files) and get_publication (which likely retrieves metadata). The phrase 'Retrieve publication content as Markdown' provides a specific verb+resource combination with output format details.

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 provides clear context on when to use this tool ('Use this to read the actual content of NIST documents') and includes practical guidance for large documents. However, it doesn't explicitly state when NOT to use it or name specific alternatives among siblings (e.g., when to use get_publication instead for metadata).

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