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

Annotations already declare idempotentHint=true and destructiveHint=false, so the safety profile is largely covered; the description adds what is actually reported (ragged row numbers, duplicate rows, empty columns), which is useful behavior beyond the annotations. However, it never discloses that this is a priced capability requiring a quote_id and an accepted_price, nor that it is non-readOnly for that transactional reason — a material omission given readOnlyHint=false.

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?

Front-loaded with the payload description, then routing, then example utterances — a sensible order. The second sentence largely re-lists the same five outputs already named in sentence one ('its delimiter, column count, ragged rows, duplicate rows and fully empty columns'), which is redundant, though the example requests earn their space.

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?

An output schema exists, so the description needn't explain return values, and the purpose/routing story is complete. What is missing for a job-submission tool with quote_id and accepted_price parameters is any mention of the quote-then-authorize workflow or cost acceptance, which an agent needs to call it successfully the first time.

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 75%, close to the threshold where the schema carries the load, and the description adds no meaning about any of the four parameters (content, quote_id, authorized_by, accepted_price). The content field's size limit and accepted delimiters are documented only in the schema, so the description neither compensates nor detracts.

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 opening sentence names a specific verb ('Describe') and enumerates the exact outputs: detected delimiter, column count, ragged rows with row numbers, duplicate rows, and fully empty columns. This distinguishes it clearly from siblings like submit_csv_preflight and submit_csv_column_profile without inspecting their schemas.

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?

Explicit routing in both directions: 'Choose this when you need to understand a file's shape ... before parsing it' and 'Do not choose this when you want the file cleaned (use csv-clean), import errors diagnosed (use csv-preflight) or per-column statistics (use csv-column-profile).' Named alternatives plus the selecting condition leave nothing to inference.

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