reconcile_compile_jobs

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

With no annotations, the description carries the full burden. It does disclose one genuinely important behavioral trait — a hard precondition that workers must be stopped, implying this mutates job state and is unsafe to run concurrently — but says nothing about idempotency, what happens to recovered jobs, or required permissions.

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?

One sentence with two load-bearing clauses, purpose front-loaded before the guard condition. Nothing is padded or repeated from structured fields.

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, but three mandatory, undocumented parameters and a state-mutating recovery operation are covered by a single sentence. An agent has no basis for supplying correct values for source_run, semantic_store, or prepare_manifest.

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%: source_run, semantic_store, and prepare_manifest appear as bare string titles with no explanation. The description supplies no parameter meaning whatsoever, leaving an agent unable to tell whether these are identifiers, paths, or store names.

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 — 'Recover interrupted compile jobs' — which is clearly distinct from siblings like compile_semantic_revision and cancel_compile_job. It stops short of explicitly naming which sibling to prefer when jobs are not interrupted, so it lands at 4 rather than 5.

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 clause 'call only when their workers are known stopped' gives an explicit precondition for invocation, which is more than most tools offer. It does not name an alternative tool for the case where workers are still running (e.g. cancel_compile_job), so it lacks true either/or routing.

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