read_document

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

With no annotations provided, the description carries the behavioral burden. It clearly communicates the read-only nature and discloses important edge-case behavior: offsets past either end are clamped rather than refused, and total_codepoints distinguishes clamped from exhausted ranges. This is strong for a read tool.

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 dense sentences, each earning its place: purpose, how to call it, and a key edge-case behavior. No filler or redundant restatement of the name or schema.

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?

For a read tool with an output schema available, the description covers what, when, how, and the main edge-case. The connection to search results makes its role among siblings clear. Nothing essential 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 description coverage is only 33%, so the description must compensate for start and end. It explains that start/end correspond to search-result offsets and recommends widening them. It adds meaning beyond the bare integer schema, but does not fully specify exact inclusivity or default-range behavior.

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 states a specific action ('read a document's text around a character range') and a clear use case ('to see what a search result was cut off from'). It naturally differentiates itself from sibling tools like search_memory by being the follow-up expansion action.

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 provides concrete guidance: pass document_id and source.start_offset/source.end_offset, widened by a few hundred characters. It implies the intended workflow after a search result, though it does not explicitly name 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.