Read Document Text

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavior beyond them: hard limits (max 12 pages / 24000 chars, max_chars up to 60000) and the shape of the response (pages_returned, next_pages, links to full Markdown and PDF). The page-marker convention is disclosed so the agent knows how to cite results.

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 tightly packed sentences: what it returns, the limits and result fields, then the guidance for long filings. The most decision-relevant facts (doc_id + page range, page markers) are front-loaded with zero 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?

There is no output schema, yet the description self-documents the return fields (pages_returned, next_pages, links) and the pagination/limit model, which is exactly what an agent needs to chain calls. Nothing essential for correct invocation is missing.

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 83%, so the baseline is 3, and the description adds genuine meaning: the default 24000-char cap versus the 60000 max_chars ceiling, and the semantics of the page range. It does not address the symbol/ticker/identifier alias cluster that the schema flags as REQUIRED, leaving that nuance entirely to 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?

The description names the exact resource and form returned: 'Markdown text of a parsed filing by doc_id and page range,' including the <!-- page N --> citation markers. This distinguishes it from siblings like get_document_summary (returns a summary) and list_company_documents (returns a list) without needing to open any 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?

It gives a concrete decision rule: 'Annual reports run 100-400 pages: read the sections you need, or download links.markdown_url to search the whole file,' which frames the paginated-read vs. full-download choice. It stops short of naming siblings such as get_document_summary that an agent might otherwise pick, so it is clear context without explicit exclusion.

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