ecg_commit_step

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

With no annotations, the description carries the full burden and does so well: it discloses refusal conditions (approve_session or unconsumed approve_run required), grant accounting (one successful commit consumes one grant, a failed commit does not), and supersede semantics (>=0.75 confidence supersedes and links supersedes; lower confidence or ambiguous target keeps both facts and opens a conflict). It also warns against hiding content in the approval dialog.

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 a dense multi-paragraph block, but it is front-loaded with the core purpose and each paragraph adds distinct value (approval dialog, id provenance, grant accounting, supersede behavior). No sentence is filler, though the volume is on the heavy side.

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 a mutation tool with no annotations and no output schema, the description covers preconditions, parameter meaning, and conflict/supersede outcomes. It stops short of describing what a successful commit returns (e.g., created fact ids, conflict references), but that is a modest omission given how much else is disclosed.

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 compensate, and it explains exchange_id (= prep_id from prepare or a new id), messages ('provenance turns'), and placements (same fields as a candidate plus action and optional supersede_existing_fact_id/target_fact_id). Only session_id is left unexplained, which is a minor gap rather than a serious one.

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?

It states a specific verb and resource ('Store approved facts for one exchange') and frames itself as 'the storage checkpoint', which is a precise scope. However, it never names or contrasts itself against the very similar sibling ecg_commit_placements, so the agent must infer the boundary from the schema and surrounding tools.

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 implies usage through the workflow ('exchange_id is the prep_id from prepare, or a new id when committing placements directly') and states the preconditions for success (approve_session or an unconsumed approve_run grant). But it gives no explicit when-not or routing guidance against the sibling commit/prepare tools, leaving the alternative selection to inference.

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