tandem_read_result

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

With no annotations, the description does meaningful work by stating that reads do not rerun, accept, or apply work, which clearly discloses read-only, non-mutating behavior. It also explains digest-bound pagination and stale-digest handling, including the rule not to combine pages from different observations. It still omits some operational details such as access requirements or error behavior beyond stale digests.

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 compact and front-loaded: the first sentence states the purpose, and the following sentences add only operational constraints. There is no filler, and the pagination and read-only rules are stated efficiently.

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?

This is a complex paginated read tool with six parameters, required fields, enums, digest handling, and no schema descriptions, yet the description leaves key calling details unexplained. It covers the pagination workflow but not what identifier means, how target and section relate, or when this tool should be chosen over siblings. The output schema helps with return values, but the initial-call context is still incomplete.

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% across six parameters, so the description must compensate, but it does not explain target, identifier, section, max_bytes, offset_bytes, or expected_sha256 directly. It hints at pagination and digests through terms like 'digest-bound UTF-8 pages' and 'stale digest', but does not map those concepts to the actual 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 states a specific verb and resource: recover a complete task or review section through digest-bound UTF-8 pages. An agent can understand the core operation without opening the schema. However, it does not explicitly distinguish this tool from nearby siblings such as tandem_result or tandem_read_artifact.

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 gives procedural usage for pagination: follow next_request unchanged, concatenate content, and do not combine pages from different observations. It does not explicitly say when to use this tool instead of sibling tools like tandem_result or tandem_read_artifact, so alternative selection is left implicit.

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