Retrieve GitHub, mail, IRC, and Delving cites for a path or symbol. Mail/IRC rarely include paths.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Source path to search (e.g. src/validation.cpp). | |
| repo | No | Optional owner/repo token to include in the query. | |
| query | No | Optional extra search text. | |
| symbol | No | Optional function or type name. | |
| snapshot | No | If true, persist this result as a dated snapshot. |
Changes observed during successful MCP inspections.
Input schema / properties / snapshotAdded value: +{
+ "description": "If true, persist this result as a dated snapshot.",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile with readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the description's burden is lower. It adds one useful behavioral trait—mail/IRC cites often lack paths—but does not describe the return format, pagination, or operational constraints. No contradiction with the annotations.
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 with zero waste: the main action and scope are front-loaded, and the mail/IRC caveat earns its place by shaping how the agent interprets results. No structured data is repeated.
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 read-only, idempotent tool with a rich annotation set, the description is serviceable, and no output schema exists to document return values. However, with 12 siblings sharing find/search verbs, the lack of explicit sibling routing or any note on result structure leaves meaningful gaps for an agent.
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 description coverage is 100%, so every parameter (path, repo, query, symbol, snapshot) already carries a meaningful description. The only added nuance, that mail/IRC rarely include paths, is a result-behavior observation rather than a parameter clarification. Baseline 3 is appropriate because the schema does the heavy lifting.
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 states a specific verb (Retrieve) and a concrete resource set (GitHub, mail, IRC, and Delving cites) scoped by a path or symbol, so an agent understands what the tool produces. It does not explicitly name a sibling to exclude, but the source-type list and the 'cites' scope separate it from the incident/precedent/spec finders among the siblings.
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?
There is no explicit guidance about when to use find_discourse versus the 12 sibling tools, and no alternatives are named. The only hint—'Mail/IRC rarely include paths'—concerns expected result quality, not tool selection. An agent must infer the tool's role without direct routing.
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.