fgis_search_document

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

Annotations already declare the tool read-only and non-destructive, so the description adds substantial behavioral detail beyond them: literal case-insensitive matching, whitespace matching across paragraph/cell boundaries, return of excerpts/offsets/next_offset, and the text_status caveat. There is no contradiction with the annotations.

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?

Six dense sentences, each carrying distinct operational value: scope, matching edge behavior, return payload, cross-tool navigation, exclusions, and an edge-case warning. The most important purpose is front-loaded and there is no filler.

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 no output schema, the description competently describes return values, pagination, follow-up reading, and the no-match caveat. It is nearly complete for the primary single-query workflow, though a few parameter semantics are left implicit.

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%, so the description must compensate. It explains query semantics and pagination/offset behavior, but it does not address limit, context, source, document_guid, or expected_sha256 beyond what their names and defaults imply. It adds meaningful value but does not fully document all seven parameters.

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 opens with a precise verb and resource: 'Find literal case-insensitive text within one public document, without a dataset.' This clearly distinguishes it from sibling tools like fgis_query_dataset and fgis_search_norms by specifying exact scope, matching mode, and document-level targeting.

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?

It explicitly names read_document as the follow-up tool and describes the pagination handoff via returned offsets. It also gives strong exclusion guidance: 'No semantic search, coefficient selection or inference', and warns to check text_status before interpreting no matches.

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