routine

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

With no annotations supplied, the description carries the full behavioral burden: it explains the {{param}} templating substitution and the record-then-save lifecycle, which is genuinely useful. But it says nothing about the stateful side effects of `start` (whether a recording session is left open), what `run` returns or how failures surface, or that `delete` is destructive and irreversible.

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?

The text is compact and front-loaded, with the identity first and the operation clips after. The semicolon-delimited pseudo-syntax is efficient but slightly telegraphic, relying on shorthand like "start = begin recording" rather than full sentences.

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?

For a five-parameter, multi-operation tool with no annotations, no output schema, and zero schema documentation, the description covers the common workflow but leaves meaningful holes: two operations unexplained, no return-value expectations, and no side-effect warnings for recording or deletion.

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 compensate, and it partly does: it shows that name, params, and steps are used together via run(name, params) and save(name, steps=[...]), and explains that entries in `params` fill `{{param}}` placeholders. It never covers the `description` parameter or the show/delete operations, and leaves the shape of `steps` objects entirely unexplained.

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 opens with a concrete noun phrase ("Saved, replayable tasks") and enumerates the operations by name: list, run, start, save. It is clearly distinguishable from siblings like act/launch because it describes wrapping recorded steps rather than performing input directly. It falls short of 5 because two enum operations (show, delete) are never described.

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 real usage guidance for the main path: it states the value proposition ("cheapest way to repeat work") and sequences start -> save versus direct save(name, steps=[...]). However, there is no guidance on when to prefer show or delete, no prerequisites (e.g., whether recording must be started before running), and no explicit when-not-to-use versus act/launch.

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