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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description adds critical behavioral context beyond that: path allowlist constraints, rejection of absolute URLs and path traversal (PATH_NOT_ALLOWED), parallel-safety caveats ('discouraged in bulk'), and upstream cost (1). It also clarifies the raw/unshaped return format. No contradiction with annotations; the read-only nature is reinforced by 'GET only'.

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?

The description is information-dense and well-structured: a one-line core purpose, then bullet points for when to use, when not to use, path constraints, parallel guidance, cost, and an example. Every section carries unique value; no filler. It is longer than typical but the tool is an escape hatch with non-obvious constraints, so the length is justified and front-loaded with the core purpose.

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?

The description covers all decision-relevant aspects: what the tool does, when to use it, when not to, path validation rules, error behavior, parallel usage guidance, and cost. Since an output schema exists (has output schema true), the raw return format is implied. For a raw-access tool with these constraints, nothing an agent needs to call it correctly is missing.

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 baseline is 3. The description adds a single combined example that demonstrates method, path, and queryJson together, which clarifies how the parameters interact. It also reinforces that method is read-only, though that's already in the schema enum. The description doesn't introduce new parameter meanings but the example adds practical usage clarity beyond the per-parameter descriptions.

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 opens with 'Power escape hatch: allowlisted Cito REST call with unshaped raw JSON in data.raw.' This states the verb (call), resource (Cito REST), and the key differentiator (raw/unshaped output). It explicitly contrasts with curated tools: 'Prefer curated tools for all standard jobs,' naming the sibling set. An agent can immediately tell this tool is for uncached, raw access and not for standard curated endpoints.

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?

Provides an explicit 'When to use' list (long-tail paths, debugging, user knows an OpenAPI path) and a 'Do not use when' clause (a curated tool covers the outcome). It also names alternatives implicitly via 'Prefer curated tools' and warns about parallel storms. This is exactly the kind of decision guidance needed for an escape-hatch tool.

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