jcm_searchArticlesSearch Confluence pages with CQL and return lean metadata such as page ID, title, space, and last modified date for quick lookups.
Search Confluence pages using CQL. Returns [{id, title, space, spaceKey, lastModified}].
| Name | Required | Description | Default |
|---|---|---|---|
| cql | Yes | Confluence Query Language string. Example: space = "KB" AND type = "page" AND text ~ "search term" | |
| maxResults | No | Max results (default 10, max 25) |
Changes observed during successful MCP inspections.
v0.10.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuine value beyond that by disclosing the return payload shape ({id, title, space, spaceKey, lastModified}), which matters because there is no output schema. It omits any note about auth requirements or what happens when the 25-result cap is hit.
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 short sentences with zero filler. The query mechanism and the resource are front-loaded, followed immediately by the return shape.
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 2-parameter read tool with full annotation coverage, complete schema descriptions and an inline return-shape disclosure, the definition gives an agent everything needed to invoke it. The remaining gaps are pagination behavior past the 25-item cap and explicit routing versus sibling lookup/search tools.
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%: the cql parameter carries a concrete example query and maxResults documents default and bounds. The description adds nothing about parameter semantics beyond that, so the baseline 3 applies. No enum or format hints are added for CQL syntax beyond the schema example.
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 and resource ("Search Confluence pages") plus the query language used (CQL), which separates it from jcm_getArticle/jcm_createArticle/jcm_updateArticle by naming the retrieval-by-query behavior. It does not explicitly say how it differs from sibling search tools like jcm_searchIssues, so it stops short of full differentiation.
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?
Usage is only implied: an agent can infer this is the tool for finding pages when it lacks an ID, whereas jcm_getArticle takes a known identifier. There is no explicit when-to-use, when-not-to-use, or named alternative for cases where CQL is unavailable or where space listing (jcm_lookupSpace) is the better path.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.