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

Annotations only say readOnly/openWorld=false; the description goes well beyond with a concrete return shape, a privacy guarantee ('values are never echoed, only paths'), an explicit price (2 credits = 2 CAD cents per successful call), and a billing-failure rule ('input that does not match the schema is rejected before billing'). That cost and data-handling disclosure is exactly the context annotations cannot carry.

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 front-loaded sentences: what is linted, what comes back, then cost terms — no filler. The return-shape sentence is dense and slightly malformed (unbalanced brackets/braces) which costs a little readability, but nothing is padding.

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 supplies the return shape itself (ok, format, findings with severity/code/path/message, counts) plus pricing and rejection semantics. For a two-parameter read-only linter, an agent has everything needed to call it and interpret results.

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 100% and both parameters are documented in-schema, including the format enum and defaults, so the description only echoes the accepted file types. It adds no format-detection or size-limit nuance (the 60,000 character cap appears only in the schema), leaving this at the baseline.

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 first sentence names a specific verb (lints) and resource (wrangler.jsonc / wrangler.toml) and enumerates exactly what is checked: name, entry point, compatibility date, secrets in vars, routes. Against lint siblings like openapi-lint, claude-md-lint and prompt-lint, the target artifact is unambiguous.

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 implied by the artifact type — you call it when you have a Wrangler config to check — but there is no explicit when-to-use framing, no prerequisites, and no routing to alternatives (e.g. openapi-lint for OpenAPI files or json-validate for mere syntax). An agent must infer the selection rule.

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