essay.debug.wipe

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

With no annotations, the description carries the full burden and does disclose non-obvious behavior: this is a destructive wipe of two files in a single call, there is no draft-then-confirm gate, and no chat card is produced (nothing user-visible). What is missing is whether the wipe is irreversible, whether anything is backed up, and what the call returns.

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?

It is short and front-loads the trigger, which is good, but the structure is telegraphic: a parenthetical name restatement, then a run of clipped fragments ('No chat card.', 'Student chat does not name those files.') whose referents are unclear. Sentences earn their place in intent but not in clarity.

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 an unannotated destructive tool with no output schema, the description supplies the operation, the trigger, and the absence of a confirmation step, which is the core of what an agent needs. It stops short of irreversibility, recovery/backup options, and return behavior, which matter for a wipe.

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 coverage is 0% and the 'speech' field has no description, so the description must compensate; 'call with speech set to what they said' does add real meaning, namely that the value is the operator's verbatim utterance rather than a formatted query. It does not address that speech is optional with a null default, or what happens if it is omitted, so the gap is only partially closed.

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 states a specific verb and resource: one call clears the prose run log and the structured ML JSONL together, which is concrete enough that an agent knows this is a debug-log wipe rather than a project/archive deletion. The opening 'essay.debug.wipe (operator speech only)' restates the name and adds a cryptic qualifier, and jargon like 'shell logs in the app folder' is ambiguous, so it is clear but not cleanly differentiated in plain language.

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 gives explicit trigger conditions — the operator asks to delete the logs, clear the run log, or clearly means to wipe the shell logs — and an explicit exclusion, 'Student chat does not name those files,' plus 'Draft-then-confirm does not apply.' It never names a sibling (e.g. essay.debug.export as the read/backup counterpart), so the alternative is left implicit.

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