call_api_raw

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, and the description is consistent with them while adding real operational detail: confirm=true is mandatory on every call, and destructive or paid actions additionally require the HOSTKEY_ALLOW_DESTRUCTIVE=1 environment gate. That is genuinely non-obvious invocation context. It stops short of describing the response shape or failure modes, which keeps it off 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?

Three dense sentences, each carrying a distinct point (what it is, what it covers, how to gate it), with the safety constraint not buried. It loses a point because the text is stored in a broken single-byte encoding, which makes the prose hard to read as delivered even though the underlying content is well-structured.

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 generic escape-hatch tool with 5 documented parameters, no output schema, and a free-form params object, the description supplies the missing pieces an agent needs: scope, the safety gate, and an external reference for the action list. It does not explain how the params object is serialized or what the raw response looks like, and the nested-params behavior is left to the schema.

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 the schema already documents resource, action, params, confirm and auth. The description reinforces the confirm requirement and gives resource-value examples (iso, s3, rhr) that partially overlap the schema's own examples. Baseline 3 is appropriate; the description does not add much beyond the schema here.

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?

Decoded, the description states a specific mechanism: a universal direct InvAPI call taking a resource + action pair, explicitly scoped to resources that lack typed tools, with concrete examples (iso, s3, rhr). It distinguishes itself from the large family of typed siblings by naming itself the fallback path, which is exactly the contrast an agent needs.

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?

Gives an explicit when-not rule ('prefer typed tools if they exist for the desired operation') plus a pointer to the external action catalogue, and names the resource families it covers. An agent can decide between this tool and, say, list_iso_images or s3_get_buckets without guessing.

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