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

Annotations declare non-destructive (destructiveHint=false, readOnlyHint=false), and the description adds rich context beyond them: the original is kept because a new outputPath is written, images/fields/untouched parts are preserved, and signed files are refused. This is exactly the extra behavioral disclosure annotations cannot supply.

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?

Dense and front-loaded: the core action leads, then output behavior, occurrence rule, part/mode options, and preservation/refusal caveats follow. Slightly run-on but every clause carries information.

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 10 parameters, low schema coverage and no output schema, the description covers the essential behavior, defaults and edge cases (signed-file refusal, preservation) but never states what the call returns. That omission is the main remaining gap.

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 20%, so the description must compensate. It explains oldText occurrence semantics, the part values (body default, header, footer, all) and mode xml, but leaves newText, inputPath and includeHeadersFooters undocumented in both schema and description, so compensation is partial.

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 ('Replace exact text in a Word .docx') and adds the distinguishing scope detail 'even where it spans formatting runs', which separates it from generic write_file/edit_block siblings. An agent can identify the operation 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?

Provides concrete when-to-use conditions: mode xml requires XML copied from read_file with docxMode xml, and oldText must occur expectedOccurrences times. It gives clear context but does not explicitly rule out alternatives or state when-not to use it.

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