record_step

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

With no annotations, the description carries the full disclosure burden and delivers real behavioral facts: SHA-256 hashing of every listed input/output file, first-call-creates-run semantics, and append-on-subsequent-calls behavior. It omits failure behavior, missing-file handling, and whether run_name reuse is safe, so it is strong but not complete.

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 core action is front-loaded in the first line, with scoping ('one step under a named run'), then behavior (hashing), then timing guidance, then run-creation semantics. Every sentence contributes; the layout is easy to scan.

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 need not be explained, and the description covers creation/append semantics and file hashing. However, for an 8-parameter mutation tool with zero annotation coverage and zero schema description coverage, gaps around error handling, run_name collisions, and the meaning of undocumented parameters leave an agent partially guessing.

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% across 8 parameters, so the description must compensate and largely does not. It implies run_name and the inputs/outputs file lists, but 'tool', 'command', 'notes', and 'exit_code' — including the default-of-0 semantics — are left entirely undocumented anywhere.

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?

Names a specific verb and resource: 'Record one executed analysis step under a named run.' Combined with 'first call creates the run; later calls append steps,' an agent can distinguish this write path from replay_run, check_run, list_stored_runs, and provenance_report. It stops short of explicitly naming a sibling to route against, so it is clear but not fully differentiated.

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?

'Use this AFTER running a tool so the agent's work becomes auditable and replayable' gives an explicit temporal/contextual trigger, which is genuinely useful routing guidance. No alternatives or explicit when-not-to-use conditions (e.g., versus provenance_report) are given, keeping it below a 5.

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