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

The description discloses key behaviors beyond annotations: conversion starts automatically upon file arrival, two delivery mechanisms (browser link vs PUT URL) with a condition for choosing, and that convert waits for the file. It explains the async nature and the dependency on a later convert call, which is valuable context not present in annotations.

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 description is compact yet dense, with no filler. It front-loads the core purpose and then explains the return and next steps. While it's a bit long, each sentence serves a purpose, and the structure (purpose → behavior → delivery → next step) is logical. Slight deduction for length, but it's well-organized.

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 properly explains the return values (import_id and two delivery methods) and the conditions for each. It also clarifies the auto-start conversion and the need to call convert. It doesn't cover potential errors or timeouts, but for this tool's complexity it is quite complete.

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 100%, so the parameters are already well-documented. The description adds a little by emphasizing that output_format is required and that conversion starts with it, and that filename carries the source format. This matches the schema and doesn't add new semantics, so baseline 3 is appropriate.

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 clearly states the tool's function: 'Get somewhere to put a local file' and distinguishes it from siblings by specifying it's for files 'not already at a URL'. It also explains the flow (conversion starts automatically, then collect via convert) and the return values, making the purpose 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?

Explicitly says this is 'the right choice for ANY file that is not already at a URL', establishing when to use it vs alternatives. It also gives a conditional for the browser-link delivery method ('when your own network cannot reach convert.online or storage') and directs the follow-up call to 'convert' with the import_id, which is clear guidance.

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