Convert a OneDrive file to PDF or JPG

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds meaningful behavior: conversion happens on Microsoft's servers (no local re-encoding), no data is lost, output is stored at a durable Hermoso URL, and the Microsoft-provided link expires in minutes. This goes beyond annotations and covers essential operational details without contradiction.

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 long but each sentence serves a purpose: it explains the mechanism, enumerates supported formats, gives examples, states a hard constraint (JPG dimensions), and describes output and permissions. It is front-loaded with the core function, and while detailed, it avoids fluff. Slightly overlong for a 4-5, but very efficient for the complexity it covers.

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?

Given no output schema, the description does a good job describing what the tool produces (a durable URL) and how to use the result ('pass straight to a render or a post'). It covers prerequisites, output behavior, and a key pitfall (expiring link). It omits explicit response structure (e.g., whether it returns just the URL or an object), but the guidance is sufficient for an agent to use the tool 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 100%, so baseline is 3. The description adds value by explaining that JPG conversion requires both width and height because Microsoft refuses the call without them, and it clarifies that fileId comes from list_onedrive_files. This exceeds the schema by providing rationale and origin context, justifying a score above baseline.

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 (convert), a clear resource (OneDrive file), and output formats (PDF or JPG). It also distinguishes itself from siblings by highlighting the broad input format support (e.g., PSD, AI, raw camera formats) that other tools in the product cannot open. This makes the tool's purpose unmistakable and separate from read/get/list tools.

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?

The description provides explicit use cases ('turn a client's deck into images', 'get a usable JPG out of a designer's PSD', 'hand someone a PDF of a spreadsheet') and a critical warning about avoiding the expiring Microsoft link. It also notes the prerequisite of OneDrive being connected. This clearly guides when and why to use the tool, and even hints at the source for the fileId (list_onedrive_files).

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