connector_github_searchSearch GitHub repositories, issues, and pull requests using natural-language queries, and create or update issues to track findings.
Search GitHub. Search repositories, issues, and pull requests. Create and update issues.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return | |
| query | Yes | Natural-language search query |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and destructiveHint=true, and the description only faintly aligns via 'Create and update issues' without warning about irreversibility or what gets modified. It does not disclose auth requirements, rate limits, or the scoping of a search. The mutation clause sits in tension with the dominant 'Search' framing, leaving the safety profile confused rather than clarified.
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?
Three short sentences, front-loaded with the primary verb, so it is compact. However the third sentence ('Create and update issues') does not earn its place given the schema exposes no create/update parameters, and its presence makes the whole definition internally inconsistent rather than simply terse.
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?
With no output schema, the description should explain return shape and pagination at least minimally, and it does not. More damaging, it advertises create/update behavior that the query/limit-only schema cannot fulfill, so an agent lacks the information needed to invoke this correctly or trust the stated scope.
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 100% with only two params (query, limit), both fully documented as a natural-language query and a max-results count, so the schema carries the load. The description adds nothing about query syntax or that it maps to repositories/issues/PRs. Baseline 3 applies.
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?
It states a verb+resource ('Search GitHub') and enumerates targets (repositories, issues, pull requests), so the read purpose is discernible. But it then adds 'Create and update issues,' which is a different verb class and unsupported by the schema, muddying what the tool actually does. It never distinguishes itself from the sibling connector_github_fetch or connector_github_act, which likely cover these operations.
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?
No when-to-use, when-not, or alternative routing is given despite the presence of connector_github_fetch and connector_github_act as clear siblings. The 'Create and update issues' claim actively misleads about a capability an agent might invoke this tool for. Nothing tells the agent which of the several github tools to prefer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.