workspace_get_dependency_reading

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

No annotations are supplied, so the description bears full behavioral burden. It does disclose some non-obvious traits (statement references and proof-local dependencies stay separate; external references yield reviewable plans; empty evidence is not independence), but omits whether the call is read-only, what permissions are needed, and what the two modes return.

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?

It is brief and front-loads the two operating modes, which is reasonable structure. However, the remaining sentences are dense jargon that reads as cryptic rather than efficiently informative.

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 four-parameter, no-annotation, no-output-schema tool sitting among many near-neighbors, the description is far too sparse. It leaves mode selection, parameter meaning, recursion behavior, and return format to inference.

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 four parameters, so the description must compensate and largely fails. 'User-selected target' loosely gestures at target_result_id and 'candidates' at max_candidates, but paper_id and recursive (default true) are never addressed, leaving core inputs unexplained.

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 offers a dual-mode purpose ('List main-result candidates or read a user-selected target with evidence') but never uses the tool's own 'dependency' framing and relies on opaque jargon like 'main-result candidates.' It does not distinguish this tool from any of the many siblings such as workspace_get_dependencies or workspace_get_result_reading_path, so an agent cannot tell which to pick.

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?

There is no when-to-use guidance and no named alternative, despite dozens of closely related dependency/result/reading tools in the sibling list. The only hints ('external references produce reviewable plans only', 'empty evidence is not independence') are behavioral caveats, not selection criteria.

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