List a SMALL page of the user's GitHub repos (name + private + updated only) so they can pick an existing one to link. LAZY: defaults to 10; pass query to filter by name rather than paging through everything. Only raise limit if the user's repo isn't shown — never dump the whole list into context.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Page size, default 10, max 30 | |
| query | No | Filter repos by name substring (preferred over paging) |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is largely covered. The description adds real behavioral context beyond that: the paged/lazy default (10), the max-30 cap implied by usage, and the context-budget discipline of not dumping the full list. It doesn't mention auth requirements or rate limits, and notably the annotations' destructiveHint=true is unexplained by the description, leaving a small gap.
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 tight sentences, front-loaded with purpose, then usage policy, then the guardrail. Emphatic caps on SMALL and LAZY reinforce the key constraint without padding.
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?
No output schema exists, and the description compensates by naming the returned fields (name, private, updated). Combined with the paging defaults and filtering guidance, an agent has everything needed to call this correctly and interpret the result.
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%, so the baseline is 3, but the description adds genuine semantics beyond the schema: `query` is framed as the preferred filter mechanism over paging, and `limit` as a fallback to raise only when needed. This conveys intent and a usage priority the schema's terse descriptions do not.
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?
States a specific verb (List) and resource (user's GitHub repos), defines the returned field scope (name + private + updated), and gives the intent (so they can pick an existing one to link). This clearly separates it from siblings like github_link and github_create.
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?
Explicitly routes the agent: prefer `query` filtering over paging, and only raise `limit` when the target repo isn't shown. It also names the anti-pattern (never dump the whole list into context), which is exactly the when-not guidance an agent needs.
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.