inspect_document

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

With no annotations, the description must carry the behavioral burden. Calling it an 'overview' and 'preview' implies a non-mutating inspection, which is useful, but it never states that nothing is modified, whether it requires the document to be currently open, or what happens with an invalid or ambiguous documentId.

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?

Two sentences, zero filler, and the highest-value information (what you get back) is front-loaded before the usage hint. Nothing repeats the tool name or title.

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?

There is no output schema, and the description compensates well by enumerating the exact counts and preview contents returned. Coverage of edge behavior — scope of the counts (body only vs. headers/footers), errors on bad IDs — is missing, which keeps it below a 5.

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 the schema already documents documentId's optionality and previewParagraphs' default and 50-cap. The description restates the concept of a paragraph preview but adds no format or behavior detail beyond the schema, so the baseline 3 applies.

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 names the specific resource ('the live document') and enumerates exactly what is returned: paragraph/section/table/inline-picture counts plus a styled paragraph preview. That distinguishes it from inspect_deck, inspect_slide and inspect_workbook on the document-type axis, though it never names those siblings explicitly.

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?

'Use this first to orient yourself in an unfamiliar document' gives a clear triggering condition and ordering relative to deeper readers like read_paragraphs or get_paragraph. It offers no exclusion cases (e.g., when you already know the document, prefer get_document_properties), so it stops short of full when/when-not guidance.

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