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

Adds real context beyond annotations: a per-call charge of $0.001, waived on failure, and the fact the result lands in the file store via a download link. Annotations already cover readOnly/idempotent/destructive hints, so this is the valuable additive layer. It does not say whether repeated calls create duplicate files, which is the one remaining behavioral question.

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?

A single dense sentence plus a cost clause, front-loaded with the artifact and scope. Nothing is redundant with the title and no 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 usefully discloses the return shape (download link in file store) and the cost. But for a 3-parameter tool with a nested filter array, filter semantics and the match flag remain undocumented, so an agent must open the schema to call it correctly.

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 only 33% and the description does not compensate: it never explains the match enum ('all' vs 'any'), and 'filters' is only alluded to as 'rows matching filters' without describing how filters combine or that up to 20 are allowed. Only 'table' is covered, and the schema already documents that parameter.

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?

States a concrete verb+resource (export a table to CSV) plus the two modifiers that matter: filtered rows and delivery to the file store. It is distinguishable from siblings like rows_query or tables_list by the CSV artifact, though it never names those siblings explicitly.

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?

No when-to-use or when-not guidance. An agent choosing between tables_export, rows_query and crm_export gets no routing signal; the only implied usage is 'you want a file'.

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