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

Annotations already cover read-only/idempotent safety, yet the description adds pricing (USD 0.005, no free tier), latency (up to 30 s), a no-logging guarantee, uncharged failures, and a prompt-injection warning about returned text. That is substantive behavior beyond the structured fields.

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 leading sentence is well front-loaded, but the body repeats the size limit twice ('up to 10 MB and 4 MP' then '10 MB/4 MP') and the run-on period-separated fragments read like a scraped feature list. Trimming the duplication would sharpen it without losing information.

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 an output schema present, return values need no explanation, and the description covers inputs, limits, cost, latency and failure modes. The closing warning mentions 'page text and on-chain strings', boilerplate irrelevant to a math-image tool, which slightly muddies otherwise complete guidance.

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%, but the description adds the crucial constraint the schema does not enforce: 'Exactly one url or image_base64' (both properties are optional/nullable in the schema). Image format and 10 MB/4 MP limits are restated, which is redundant with the schema.

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 and resource ('Recognize one printed equation as LaTeX') and scopes it to printed math crops, which clearly separates it from the generic ocr_image sibling. An agent can decide without opening the schema.

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?

'Printed equation crop only' and 'Approximate, not a solver' set clear use and non-use conditions, and 'unsupported, empty or truncated results fail uncharged' tells the agent what failure looks like. It never names an alternative tool (e.g. ocr_image) for non-equation images, so it falls short of full routing guidance.

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