Free diagnostic for MCP/tool description quality. Use before publishing a tool to identify missing purpose, trigger, input, output and constraint cues.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| description | Yes | ||
| inputSchema | No | ||
| outputSchema | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, and the description aligns by calling it a 'Free diagnostic' – confirming no mutation. The description also adds that it identifies specific missing cues (purpose, trigger, input, output, constraints), which is useful behavioral context. No contradiction.
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 concise sentences, front-loaded with purpose and context. 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?
The description lacks information about what the tool returns or how it behaves beyond identifying missing cues. With no output schema, the agent cannot predict the result format. For a diagnostic tool, it should explain the outcome (e.g., a report with suggestions).
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 coverage is 0%, and the description does not explain parameters beyond the context that it analyzes tool descriptions. It does not explicitly clarify that 'name' and 'description' are the tool being analyzed, or that inputSchema/outputSchema are optional. The description should compensate for the lack of schema descriptions but doesn't.
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 it is a diagnostic for MCP/tool description quality, identifying missing purpose, trigger, input, output, and constraint cues. This is specific and distinguishes it from sibling tools like optimize_tool_description or rag_quality_report.
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 says 'Use before publishing a tool' which gives a clear context, but it does not explicitly state when not to use it or mention alternatives. It implies a pre-publication diagnostic but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets one of three clearly labeled domains (tool descriptions, RAG evidence, structured output), and the free vs. paid split is explicit in most descriptions. The RAG pair (inspect_rag_evidence vs. rag_quality_report) could still be confused because both sound like diagnostic reports, but the descriptions make the distinction workable.
Five of six tools follow a clear snake_case verb_noun pattern (analyze_, inspect_, optimize_, repair_), and the domain prefixes keep the set cohesive. rag_quality_report breaks the pattern by leading with the noun rather than a verb, creating one inconsistency.
Six tools is a well-scoped set for a QA suite spanning three areas, with one free diagnostic and one paid follow-up per area. No tool feels redundant or missing as a category.
Tool-description and structured-output workflows have both a diagnostic and a remediation/plan tool, so those paths are reasonably complete. The RAG evidence path offers only inspection and a paid report, with no repair or optimization tool, leaving that track without a clear remediation step.
