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

Annotations say readOnlyHint=false and destructiveHint=true, and the description builds on this by naming exactly which operations mutate (DOCX/XLSX edits can replace input; PDF writes create/replace output) and which is safe (read_document is read-only). This is strong context beyond the annotation flags.

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?

Three dense sentences with no filler: purpose, mutation semantics, and routing alternatives all earn their place. Front-loaded with the primary use case.

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 the rich conditional schema, output schema, and annotations, the description covers what remains: the domain, the read-only exception, destructive defaults, and sibling routing. Nothing essential is missing for selecting and invoking the tool.

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 schema already documents every parameter. The description adds general guidance to pass only validated parameters and notes output replacement behavior, but no operation-specific parameter semantics beyond the schema.

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 specific verb and resource: structured document content spanning read/edit/merge/split/extract/inspect. Explicitly distances itself from read_file and control_computer, so an agent can distinguish it without opening the 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?

Opens with a clear when-to-use trigger ('structured document content') and closes with explicit alternatives (read_file for plain text, control_computer for interactive Office UI). Also instructs to choose one operation and pass only validated parameters.

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