context_search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full load and does well: it discloses that results are untrusted, that approved sources are refreshed before searching (a side effect with latency implications), and warns against following embedded instructions (prompt-injection defense). It omits auth requirements, rate limits, and pagination, which keeps it out of the top band.

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?

Four tight sentences, front-loaded with what is searched, then return shape, then the follow-up path, then the safety warning. No filler and nothing repeated from structured fields.

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?

There is no output schema, and the description still characterizes the return payload (source_label, link, opaque record_id) and the intended citation behavior. The main gap is the undocumented limit parameter, which matters for a search tool.

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 0%, so the description must compensate. It only implies the existence of a query ('search ... conversations') and never mentions the limit parameter or its 1-20 bound, leaving half the input surface undocumented.

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 (search) and a specific resource (imported/approved ChatGPT, Claude and Claude Code conversations), which immediately separates it from the sibling context_read. An agent can tell what this tool retrieves without opening the schema.

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 to the sibling: 'use context_read with record_id for more context,' which tells the agent when to follow up elsewhere. It does not state when not to use the tool (e.g., when no approved sources exist), so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.