rec_export

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description usefully adds that a file is written and where it lands by default ('next to the JSONL') - context the annotations do not carry. However, that file-writing side effect sits awkwardly with a readOnlyHint=true claim, and the description never says whether an existing CSV is overwritten, whether directories are created, or whether the recording is disturbed - gaps that matter for a tool that touches the filesystem.

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?

Two sentences with zero filler: the action and format options lead, the default output location follows. The parenthetical format definitions are dense but each word is load-bearing for an agent choosing between formats.

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 return values need not be explained, and the annotations cover the safety profile. What remains missing is material: the meaning of `id` and `symbols`, and the overwrite/overwrite-failure behavior of the output file, which are exactly the gaps a 4-parameter, 0%-coverage schema leaves open.

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 description must carry the parameter burden: it explains `fmt` values in real detail (csv_wide column-per-symbol forward-filled vs. csv_long long format) and the `out_path` default. It says nothing about `id` (which recording) or `symbols` (which subset to include), leaving two of four parameters semantically undefined.

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 ('Export a recording to CSV') and enumerates the two supported output shapes with their exact column layouts, so the agent knows precisely what artifact it produces. It never names or contrasts an alternative sibling (e.g. rec_read, rec_compare, exp_report), so differentiation is implicit through the 'recording' resource rather than explicit.

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 when-to-use guidance: nothing says when to export vs. read the recording in place (rec_read) or compare it (rec_compare), and no preconditions (recording must exist/be stopped) are stated. Format selection is described, but that is parameter choice, not tool-choice guidance.

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