ecg_record_provenance

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

No annotations exist, so the description carries the full burden and does so well: it discloses that nothing durable is written, that storage is deferred and conditional, and that consent gates the persistence. It stops short of covering idempotency or what happens if no commit follows.

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?

Three short, front-loaded statements with no filler; the negative constraint appears in the first sentence and the message format is compactly specified. The mid-text code fence breaks flow slightly but 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?

For a staging tool with a nested message payload and no output schema, the definition covers the deferred-write model, consent gating, and message format. It leaves session/exchange identifier meaning and any size limits or idempotency behavior unaddressed.

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. It documents the shape and semantics of the `messages` parameter in detail ('{"role": "user"|"assistant", "content": "..."}'), but says nothing about `session_id` or `exchange_id`, leaving two of three required params undocumented.

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 ('Stage conversation turns') and immediately scopes it with 'Does not write durable memory', which distinguishes it from the persistence side of the sibling set. It ties itself to ecg_commit_step, giving partial sibling differentiation, though it doesn't distinguish against staging-adjacent tools like ecg_discard_proposal.

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?

Explicitly states the persistence condition ('Full text is stored only if a later ecg_commit_step succeeds under consent'), which tells the agent when this tool's effect becomes durable and implies the commit dependency. It lacks an explicit when-to-use/alternative routing statement, but the context is clear.

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