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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds useful context — 'No data is modified' and 'Requires authentication' — but says nothing about pagination or result caps on list_files, how an inaccessible or non-existent file_id is reported, or what the response looks like. With annotations carrying the safety burden, this is adequate but not rich.

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?

It is front-loaded with a one-line scope statement, then a kind taxonomy, then a bulleted action list — easy to scan and appropriately sized for a two-action tool. There is minor duplication: 'No data is modified' restates readOnlyHint, and the kind-to-tool mapping appears twice in slightly different form.

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?

For a read-only metadata tool with no output schema, the description covers the scope, both actions, the kind filter and the authentication requirement, which is enough to invoke it correctly. The remaining gap is insufficient disclosure of return details — the description mentions kind and web URL for get_file_info but not what list_files returns per entry or whether results are limited.

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?

The schema is only a generic action/params envelope with an untyped params object, so the description is the sole source of parameter meaning. It supplies the actual accepted action strings and the shape of their arguments, including the concrete kinds values ('["GRID"]', '["DOC"]', '["SLIDE"]') and the semantics of file_id. Without this text an agent could not construct a valid call.

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 states a specific verb and resource ('Read-only file metadata operations on Quadratic files') and enumerates the two concrete actions, list_files and get_file_info, with their arguments. It also maps file kinds to the sibling tools that edit them (GRID→read_data/write_data, DOC→doc_read/doc_write, SLIDE→slide_read/slide_write), so an agent can separate this metadata tool from the content-editing siblings without opening a 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?

It clearly frames the context: use this to discover or inspect file metadata, and use the per-kind tools to read or write content. The kinds filter is explained as a way to limit listing to GRID, DOC or SLIDE. What's missing is an explicit 'when not to use' statement — e.g. that this returns metadata only and never content, so an agent must chain to read_data/doc_read/slide_read after resolving an id.

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