tnd_get_updates

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

With no annotations, the description carries the full burden and only says what is returned. It does not disclose that setting start=true triggers a new scan (a mutating, potentially slow operation), whether that scan is synchronous or how long it takes, whether prior results are replaced, or what happens when no scan has ever been run.

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?

One front-loaded sentence naming the resource and the return contents with no filler. It is efficient but too short to carry the behavioral weight the tool needs given the absence of annotations.

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?

The tool is simple (one optional boolean, no nested objects, no output schema) and the description covers what comes back, which is the core need. However, for a tool whose only parameter can kick off a scan, leaving that side effect and any preconditions unexplained is a meaningful gap.

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 100%, and the single parameter 'start' is already documented as a boolean defaulting to false. The description adds nothing about it, so the documented baseline of 3 applies; its main omission is the consequence of flipping start to true.

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 gives a specific verb and resource: reading the update-scan results for already-downloaded books, plus the two values returned (updatable count, failed chapter count). It does not distinguish this from nearby siblings such as tnd_check_chapters or tnd_get_book_status, which also sound like they report chapter/update state.

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 statement of when to call this rather than tnd_check_chapters, tnd_get_book_status, or tnd_get_status, and no note that a scan must already exist before results can be read. The only usage-shaped signal, that start defaults to false, lives in the schema rather than the description.

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