confluence_raw_request

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

With no annotations, the description must carry the burden. It discloses that GET is default, non-GET requires additional env flags and confirm=true, and DELETE needs destructive opt-in. This is good behavioral transparency for a raw request tool, but it doesn't mention rate limiting, response format, or error handling (e.g., 404s), which could matter for an agent invoking raw paths. Still, the key safety and opt-in constraints are clearly disclosed.

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, tightly packed with essential information. The first sentence establishes purpose and scope, the second details method constraints. Every sentence earns its place, though the mention of DELETE opt-in could be integrated more smoothly, but it remains concise.

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?

Given the tool's complexity (6 params, variable methods, env-dependent behavior) and missing annotations/output schema, the description provides substantial necessary context: path restrictions, method constraints, and opt-in requirements. It lacks some details like response format or fail modes, but for a raw API tool, the core protocol is well-covered. It's likely complete enough for a competent agent to call it safely.

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 covers the critical parameters: method (GET default, non-GET restrictions), path (must be under specific prefixes), confirm (true for non-GET), and destructive opt-in for DELETE. It doesn't explicitly explain query, body, max_chars, but these are clear from their names and the schema, and the description's focus on the most safety-critical parameters adds significant value.

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 clearly states it is a raw API caller for allowlisted Confluence paths, with specific path prefixes. It differentiates itself from named siblings by saying it is for operations not covered by a named tool, which gives clear purpose and distinguishes it from the many more specific tools it sits alongside.

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?

The description implies usage: when no named tool covers the operation, use this. It also provides critical conditions for non-GET methods (CONFLUENCE_ALLOW_RAW_WRITE=true, confirm=true, destructive opt-in for DELETE). However, it doesn't explicitly name an alternative or say when NOT to use it (e.g., when a named tool exists), though that's strongly implied.

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