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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and the description adds real context: idempotency/retry guidance, canonicality (trust actual_tool_output), and a confirmation boundary stating no extra confirmation is needed for this read. It never reconciles the readOnlyHint=false annotation with the word "read," which is a minor gap given the tool mutates state by splitting PDFs.

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 opening sentence is well front-loaded, but the bulk of the text is a full end-to-end import narrative (upload via curlExample, reviewMarkdown presentation, multiple-choice confirmation wording) that belongs to create_import_intake, confirm_import_intake, and the review tool. For a two-parameter read tool this is grossly over-sized and buries the operative instruction.

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, and the description explains the loop-termination signal ("remaining is 0") and downstream review presentation, so the workflow context is present. However, it says nothing about this tool's own return shape beyond "remaining," nor about the required intakeId, leaving a genuine gap for a tool whose whole job is producing per-file read results.

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% and the description never mentions intakeId or _corply_context at all. It discusses acknowledgedIssues, reviewHash, and values, but those belong to confirm_import_intake, so the description actively risks steering the agent toward the wrong tool's parameters rather than compensating for the undocumented ones.

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 first sentence states a specific verb and resource: "Have Corply read the uploaded files: identifies each document, reads it, and splits a PDF only when it holds several documents." It also distinguishes itself from siblings by naming get_import_intake_review, create_import_intake, add_import_intake_url, and confirm_import_intake as the surrounding steps, so an agent can place it in the flow.

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 gives explicit operational guidance: "Reads a few files per call; repeat until remaining is 0, then call get_import_intake_review," and states the prerequisite (authenticated active company access) plus the ordering relative to create_import_intake and confirm_import_intake. When-to-call and the hand-off condition are both unambiguous.

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