Remove a conversion job

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

The description adds substantial behavioral detail beyond the annotations: by default it only forgets the job_id, leaves out_dir/.state/<job_id> intact, and with delete_files=True deletes only the scratch directory. It explicitly states that original mp3/epub and already-delivered files in out_dir are never touched, even when delete_files is true. This aligns with and enriches the destructiveHint=true annotation without contradicting it.

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 description is well-structured with a concise prose section followed by Args and Returns sections. It is front-loaded with the core behavior and adds essential nuances about disk state and delete semantics. It is slightly redundant with the schema (e.g. repeating delete_files semantics), but the added clarity about what is and is not deleted earns its place.

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?

The description fully covers what an agent needs to call this tool correctly: the registry-only default, the disk-deletion behavior, the boundary of what is never touched, the input parameters, and the return format including the error case. With annotations already signaling destructive and idempotent behavior, no important operational context is missing.

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?

Context signals indicate 0% schema description coverage, so the description must compensate for parameter meaning. It explains job_id as the registry key and delete_files as controlling whether the working directory is deleted. It also includes the default behavior ('By default this only forgets the job_id') and the exact effect of delete_files=True. The description does not explicitly state that job_id comes from audiobook_start_conversion, but the schema itself does, so this is adequately covered.

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 begins with a specific verb and resource: 'Remove a job from the registry.' It goes beyond the title by clarifying that removal is from the registry only, not necessarily from disk, and it names the related start tool implicitly through the resume behavior. This clearly distinguishes the tool from siblings like audiobook_start_conversion and audiobook_continue_conversion.

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?

The description clearly explains the effect of calling the tool with default settings versus delete_files=True, and gives the important consequence that the same job_id/mp3/epub/out_dir can resume a forgotten job. It does not explicitly name alternatives or say 'use this when...', but the context and behavioral consequences are clear enough for an agent to decide.

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