read_dupe

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

With readOnlyHint/destructiveHint already covering safety, the description adds real behavioral value: output is lossless (nothing truncated), and response size can blow up on large dupes. It doesn't mention failure behavior when the name doesn't resolve or whether the payload can be filtered.

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?

Three short sentences with the key constraint (large responses, paginated alternative) placed last where it is most actionable. The middle sentence about typed keys and tags is mildly informational but cheap. No padding or repetition.

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 is not obliged to explain return structure — yet it spends its budget on format details while leaving the sole input and the not-found/failure path unspecified. For a single-lookup reader this is adequate but has clear gaps an agent would hit on first call.

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?

There is one required parameter, 'name', with 0% schema description coverage, so the description carries the full burden — and it says nothing about it. It never clarifies whether 'name' is a dupe name, a model name, or an ID, nor any naming/case conventions. The format notes about typed keys and tagged vectors describe output, not the input parameter.

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 the return artifact ('a lossless adv2mcp-json-v1 document') but never plainly says it reads a single dupe by name and returns its full unsummarized contents. The resource is only inferable from the tool name, and the format token 'adv2mcp-json-v1' is opaque without prior knowledge. It does implicitly distinguish itself from inspect_dupe by calling out pagination.

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 a concrete routing rule: large dupes produce large responses, so use inspect_dupe when pagination matters. That names the alternative and the condition selecting it. It stops short of explicitly saying when this tool is the right choice (e.g. 'use when you need the complete dupe, not a summary').

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