ref-tools-mcp

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

While annotations confirm read-only safety, the description adds critical behavioral details: output is converted to markdown format, and the hash fragment must be preserved from search results. Does not cover error handling or rate limits.

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?

Two sentences, zero waste. First sentence front-loads the action and output format; second sentence provides the critical workflow constraint. Every word earns its place.

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?

Complete for a simple single-parameter read tool: explains output format (compensating for missing output schema), documents sibling relationship, and covers the hash detail. Minor gap: no mention of error handling for invalid URLs.

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?

Despite 100% schema coverage (baseline 3), description significantly enriches the 'url' parameter by specifying its provenance (must come from ref_search_documentation) and format constraints (must include #hash), adding semantic meaning beyond the schema's generic description.

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?

Specific verb ('Read') + resource ('content of a url') + output format ('as markdown'), and explicitly distinguishes from sibling by stating the URL must come from 'ref_search_documentation', establishing clear workflow boundaries.

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 clear prerequisite by stating the EXACT url (including #hash) must come from 'ref_search_documentation' results. However, it doesn't explicitly state when NOT to use the tool or mention if arbitrary URLs are acceptable.

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

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

Annotations already declare readOnlyHint=true, establishing the safe read-only nature. The description adds valuable scope context by mentioning 'private resources like repos and pdfs', but omits details about authentication requirements for private access, rate limits, or the specific format of search results returned.

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 consists of exactly two sentences: the first states the search capability and scope, the second establishes the relationship with the sibling tool. Every word earns its place without redundancy or unnecessary elaboration.

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 single-parameter input, readOnly annotation, and lack of output schema, the description is substantially complete. The reference to ref_read_url cleverly implies that this tool returns references/URLs rather than full content, though explicitly stating the return value format would provide perfect completeness.

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?

Input schema has 100% description coverage for the single required parameter, establishing a baseline score of 3. The description mentions 'private resources' which aligns with the schema's ref_src=private option, but does not add additional syntax guidance, format examples, or semantics beyond what the schema already provides.

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 uses the specific verb 'Search' with the resource 'documentation' and clearly defines the scope as 'web or github as well from private resources like repos and pdfs'. It effectively distinguishes from sibling tool ref_read_url by stating that tool is used to 'read the content of a url', implying this tool performs search rather than content retrieval.

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 explicit workflow guidance by directing users to 'Use Ref 'ref_read_url' to read the content of a url', establishing a clear alternative for the read operation and implying when not to use this tool (for reading full content). This creates a complete when-to-use guideline for the tool pair.

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