inspect_document

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

With no annotations, the description carries the full behavioral burden. It does disclose the data categories returned and implies a read-only inspection, but says nothing about permissions, failure behavior for unknown IDs, response size/truncation, or rate limits.

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?

A single front-loaded sentence that names the action, the target, and the returned data with no filler. Every clause earns its place.

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?

An output schema exists, so return-value shape need not be explained, and the description still helpfully previews the facets. However, for a two-required-parameter tool with zero schema coverage and no annotations, the unexplained run_id and absent error/permission context leave real gaps.

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 0% for two required parameters. The phrase 'by ID' loosely maps to document_id, but run_id is never mentioned or explained in the description, leaving the agent to guess its meaning and whether it scopes the document lookup.

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 (inspect) and resource (a single indexed document) and enumerates the facets returned: full text, metadata, engagement, provenance. It implicitly separates itself from search_documents/search_semantic by being ID-scoped and singular, but it never names an alternative outright.

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?

There is no when-to-use or when-not-to-use guidance, and no mention of prerequisites beyond needing an ID. The agent must infer that IDs come from a prior search step and that this is the follow-up deep-dive call rather than a search.

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