rec_read

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

Annotations only declare readOnlyHint/destructiveHint; the description goes further by disclosing output shape (one row per PLC timestamp, one column per symbol), the null-cell semantics when a symbol has no sample, and the caution that a filled cell is not a sample. This is meaningful behavior beyond the annotations, though auth/rate/size limits are untouched.

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 the core action, then progressively explains wide and fill. The wide/fill sentence is dense but every clause conveys real behavior; little is wasted.

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 needn't be explained, and the mode semantics are well covered. But with 7 params at 0% schema coverage, the absence of any documentation for the time-window and symbol-selection parameters leaves gaps an agent must guess at.

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 carries the full burden, yet it only explains fill and wide out of 7 parameters. Critical filters like id, symbols, t_from_ms, t_to_ms, and max_rows receive no semantic explanation anywhere.

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+resource+scope: "Read a time window of a recording from its file." This clearly separates it from control siblings like rec_start/rec_stop and from rec_export or rec_list. It stops short of explicitly naming an alternative sibling, but the purpose is unambiguous.

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?

It offers contextual guidance for the fill mode ("handy for 'what else was true when X happened'") and notes it works on finished recordings from earlier sessions. However, it never says when to reach for rec_read versus rec_export, rec_capture, rec_snapshot, or ads_read, so the agent must infer the routing.

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