search_spansSearch archived conversation text case-insensitively to find messages containing a term. Returns span file, message index, role, and snippet per hit.
Case-insensitive search of the conversation text compaction archived. One line per hit: span file, message index and role, snippet.
| Name | Required | Description | Default |
|---|---|---|---|
| max | No | ||
| run | No | only this proxy run id | |
| term | Yes | text to find |
Changes observed during successful MCP inspections.
v0.10.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds genuinely new behavior: case-insensitive matching and the exact one-line-per-hit output format (span file, message index, role, snippet). It omits pagination/default behavior when max is unset, which keeps it from a 5.
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 tight sentences with zero waste: the search scope is front-loaded and the return format follows immediately. Nothing is restated from the title or schema.
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 usefully specifies the return format, and the annotations cover safety, so an agent has most of what it needs. It stops short of explaining default scope (all runs vs one) and the default for the optional max parameter.
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 67%: 'run' and 'term' are documented in-schema while 'max' is not. The description adds matching semantics for term (case-insensitive) but says nothing about max or the default scope across runs, so it only partially compensates for the coverage gap.
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+resource (search of the conversation text compaction archived) and describes the result shape, so the agent knows exactly what it retrieves. It does not explicitly distinguish itself from read_span, its closest sibling, so it falls short of a 5.
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 or when-not-to-use guidance and no mention of alternatives such as read_span or guardian_status. The agent must infer that this is a discovery step before reading a specific span; nothing in the text says so.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.