read_context

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

Given annotations already declare readOnlyHint, idempotentHint true, and openWorldHint false, the description correctly implies a read-only, idempotent operation. The description adds value by specifying the conditional behavior ('when immediate neighbor refs are not enough'). No contradiction found.

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?

The description is a single, relatively concise sentence. It efficiently introduces the tool's conditional nature. One could argue 'nearby' is redundant, making the sentence slightly less concise than ideal, but it's still effective and not verbose.

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 the description doesn't need to detail return values. With 3 parameters (1 required), it's a simple tool. The description, combined with the schema, gives a minimally viable understanding of the tool's input/output. Missing mention of the 0-3 range for before/after is a minor gap.

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 0%, so the description must explain parameters. It effectively describes 'after' and 'before' implicitly through the concept of 'immediate neighbor refs' and 'expand nearby', but it does not mention the 'id' parameter or explain the numeric bounds of after/before (0-3). This forces the LLM to infer some meaning.

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 clearly states the action ('Expand nearby refs') and the resource ('chunk'). The purpose is discernible: this tool finds and returns the surrounding context around a specific position. However, it could better distinguish itself from siblings like 'read_section' by explaining what makes it different.

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?

The description implies usage context ('when immediate neighbor refs are not enough'), setting an expectation of fallback behavior. However, it provides no negative guidance on when NOT to use this tool or how it differs from alternatives like 'read_section' or 'search_within_page'.

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