Too many MCP tools makes agents pick the wrong one. Given your tool list and usage, get keep / merge / remove recommendations to get under the 10–15 tool guideline.
| Name | Required | Description | Default |
|---|---|---|---|
| tools | Yes | JSON array of {name, category?, callsPerDay?, description?}. Accepts a JSON array, or a JSON string containing one. | |
| targetToolCount | No | Target number of tools to keep (default 12) |
Changes observed during successful MCP inspections.
Input schema / properties / tools / descriptionPrevious value: -"JSON array of {name, category?, callsPerDay?, description?}"New value: +"JSON array of {name, category?, callsPerDay?, description?}. Accepts a JSON array, or a JSON string containing one."Input schema / properties / tools / typePrevious value: -"string"New value: +[
+ "string",
+ "array",
+ "object"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior. It correctly frames the tool as advisory by saying 'recommendations,' which signals no destructive side effects, but it does not describe what the recommendations contain, how usage values affect the analysis, or whether any actual merging or removal is performed.
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 compact at two sentences and front-loads the motivating problem before stating the action. Every sentence contributes to understanding why and when to use the tool, with no filler or redundancy.
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 simple two-parameter advisory tool, the description sufficiently conveys the expected input and the nature of the output. There is no output schema, so the tool would benefit from slightly more detail on the shape of the recommendations, but the current description is enough to call the tool correctly.
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 input schema already documents both parameters fully, including the JSON array form for tools and the default for targetToolCount. The description adds helpful context that the tools list should include usage ('tool list and usage'), but it does not add any syntax or format details beyond what the schema 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 a specific verb phrase 'get keep / merge / remove recommendations' applied to a tool portfolio, and it ties the outcome to the 10–15 tool guideline. This clearly communicates what the tool does and roughly distinguishes it from calculators and search-like siblings, though it never names a sibling explicitly.
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 opening sentence, 'Too many MCP tools makes agents pick the wrong one,' provides a concrete trigger condition, and 'get under the 10–15 tool guideline' defines the goal. It does not mention alternatives or exclusions, but the context is clear enough for an agent to know when this tool is appropriate.
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.