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

Adds substantial behavior beyond the annotations: required authority (decide for the kernel's proven operator wallet or admin), specific error codes (401 no credentials, 403 operator_proof_required, 403 no-kernel non-admin), the constraint that body kernelId cannot select the auth target, and success semantics (receipt with stored: true). The explicit warning that stored: false means nothing was stored and must never be followed by status completed is high-value operational context.

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 purpose is front-loaded, but the description repeats the 'decide' authority concept three times across separate sentences, which pads length. It is informative but not tightly structured, with some redundancy that could be consolidated.

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?

No output schema exists, so the description rightly covers return semantics (receipt with stored: true/false). Combined with rich auth and error disclosure, it is nearly complete for a mutation tool, with the main gap being per-parameter meaning for the 0%-coverage schema.

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%, so the description must carry parameter meaning. It clarifies kernelId's role (cannot choose the authorization target) and describes the evidence payload contents (device ID, execution timestamp, result payload, event timeline), but jobId is left entirely unexplained and there is no format guidance for any parameter. Partial compensation only.

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: 'Operator pushes evidence bundle from a completed job execution,' which is concrete and distinguishable from generic archive/list tools. It does not explicitly differentiate from close siblings like submit_evidence_hash or commit_evidence, but the scoping to a completed job execution and operator role is fairly clear.

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?

Provides context that it applies to a completed job execution and states auth preconditions (decide authority), but never says when to choose this over alternatives such as submit_evidence_hash, archive_evidence, or register_job_evidence_ip. Usage is implied by the auth/error conditions rather than stated as guidance.

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