rec_status

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

Annotations already establish readOnly/destructive=false, and the description adds real semantics beyond them: it disambiguates missing_samples (holes in the PLC timeline, cycle mode) from dropped (lost on this PC) and backlog, and spells out the scope state machine (recording | finishing | finished | stop_unknown) including the stop_refused edge case. It stops short of saying whether the call blocks, how expensive it is, or how stale the snapshot may be.

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?

Lead clause is front-loaded and useful, but the rest is one long comma/semicolon-spliced enumeration that reads as a data dump rather than guidance, and much of it duplicates the output schema. It is not padded with fluff, but the structure makes it hard to scan.

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?

A read-only status tool with an output schema, so return-shape explanation is not required — and the field list arguably overlaps gratuitously with that schema. The real remaining gap is provenance of the id and whether the tool is valid against finished recordings; everything else an agent needs to invoke it is present.

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?

Only one parameter (id) with 0% schema description coverage, and the description never mentions it or how an id is obtained (rec_list/rec_start). The phrase 'one recording' implies the id identifies the recording, which is the entire semantic contribution — marginal, but the schema itself is trivially self-evident for a single string key.

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?

Opens with a specific verb+resource: 'Live status of one recording', then enumerates the concrete data it reports (samples, rate, missing_samples, dropped, backlog, armed/triggered, last value per symbol). It never names which sibling to use instead (rec_stats, rec_read, rec_list), so an agent must still infer the boundary against those, but the scope of what this tool returns is unmistakable.

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?

Usage is only implied: 'live' status suggests polling during an active recording, and the note that 'rec_stop asks again' when state is recording with stop_refused gives one concrete routing hint to a sibling. There is no explicit when-to-use versus rec_stats/rec_read/rec_list, and no statement about whether it works on finished recordings.

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