neurover_draft_view

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

Annotations already declare readOnlyHint=true, destructiveHint=false, so safety is covered; the description usefully adds that this shows 'exactly what will go to the server', i.e. a non-submitting preview with warnings surfaced. It does not disclose token lifetime/expiry, what happens if the token is stale or already submitted, or error behavior — relevant for an openWorldHint tool keyed by a token.

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?

A single front-loaded sentence with no filler; the enumerated return contents are the useful part. The dash-separated list is slightly dense but adds information rather than noise.

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 one-parameter read-only tool with no output schema, the description does the important work of enumerating what is returned, which largely substitutes for a missing output schema. It still leaves gaps on token provenance and expiry, which an agent needs to call it successfully in an open-world, session-based workflow.

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?

One required parameter with 0% schema description coverage: the schema only types it as a UUID pattern. The description partially compensates by saying the token identifies a 'подготовленный запрос', implying it originates from a preparation step, but it never says where the agent obtains that token or how long it stays valid.

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?

States a specific verb and resource ('Показать подготовленный запрос по токену') and enumerates exactly what the result contains: final prompt, references table, settings, warnings. An agent can distinguish this read-only preview from write-oriented siblings like neurover_submit_generation or neurover_prepare_generation, though no sibling is named explicitly.

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 phrase 'ровно то, что уйдёт на сервер' implies this is a pre-submission preview step, so usage is inferable. But there is no explicit when-to-use, no statement that the token must first be obtained from a prepare_* call, and no guidance on when to use this versus calling the preparation tools directly.

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