get_passage

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavior: the retrieval widens by neighbouring chunks and is capped at 3 either side, which the schema does not state. It says nothing about ordering, behavior on an invalid chunk_id, or what a returned chunk object contains.

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?

Two short sentences with the identifier and the retrieval scope front-loaded; nothing is wasted. The trailing fragment 'Text is paper data' is clipped enough to be slightly ambiguous, which keeps it from a 5.

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, so the description is the only place the return value could be characterized, and 'Text is paper data' is too terse to say what an agent actually receives. For a simple two-parameter read tool this is close to sufficient, but the return shape and error behavior remain unclear.

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 has to carry the parameters. It does explain chunk_id implicitly (the passage identifier) and gives real meaning to 'context' as neighbouring chunks either side, bounded at 3. It never states that context defaults to 1 or what the units mean at the boundaries, leaving part of the contract unstated.

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?

Names a specific verb and resource ('Read a passage') plus the key it is addressed by ('chunk_id'), which is enough for an agent to distinguish it from search-style siblings. It does not explicitly contrast itself with get_table or search, so it stops short of full sibling differentiation.

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?

'Text is paper data' hints that this tool is for retrieving prose rather than tables, which implicitly points an agent away from get_table. There is no explicit when-to-use statement, no preconditions, and no named alternative for the table case.

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