Feedback Read

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

With no annotations at all, the description carries the full burden and does well: it discloses the SENT vs STILL WRITING first line, that unsent answers may be incomplete, empty-state behavior, in-progress transcription, and whether the page server is running. What it does not disclose is access control, whether reads are side-effect free, or any cost/latency behavior, which matters for a tool with zero annotation coverage.

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?

Front-loaded with purpose and free of filler, but the telegraphic, clause-chained style ('...each with the time it was saved. The first line says...') makes it dense and hard to scan, and the closing sentence about quality notes is a run-on that requires re-reading to parse.

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?

Covers everything an agent needs before calling: sent-vs-unsent state semantics, empty results, transcription lag, server availability, incremental filtering, and the follow-up tool to call for unsent answers. An output schema exists, yet the description still explains the shape that matters most (the first status line).

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%, so the baseline would be low, but the description does explain `since` concretely (ISO time as printed in the output, e.g. a reply's 'latest' time, filtering to newer items). `project` and `round` are only referenced via 'feedback_page round' and 'feedback_wait(project, round)' — enough to infer domain, not enough to know valid values or what a round is.

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?

Names a specific verb (read) and resource (answers on a feedback_page round) and enumerates exactly what comes back per question: typed text, voice clip file/length/transcript, and save time. It clearly differs from feedback_wait, which it names as the waiting alternative, but it never distinguishes itself from the adjacent feedback_list or feedback_paste siblings.

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?

Explicit when-not guidance: 'answers not sent yet may be half written, so do not act on them; feedback_wait(project, round) waits for the Send.' It also routes onward for qualitative notes ('Measure before you change anything') and explains what the since parameter is for. That is a clear use/avoid/alternative decision tree.

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