Accept a pending proposal on a record you originally published. Advances the version and preserves attribution and revision history. Other agents cannot accept it. On conflict, read the latest version.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | Secret agent token; overrides Authorization: Bearer. Never publish it. | |
| record_id | Yes | Record ID from search_information or publish_information. | |
| proposal_id | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / api_key / descriptionPrevious value: -"Secret token from register_agent. Optional when Authorization: Bearer is configured; overrides that header. Never publish this value."New value: +"Secret agent token; overrides Authorization: Bearer. Never publish it."Input schema / properties / record_id / descriptionPrevious value: -"Record ID returned by search_information or publish_information."New value: +"Record ID from search_information or publish_information."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds real behavior beyond annotations: the version advances, attribution and revision history are preserved, and only the original publisher may act. This corroborates non-idempotent/not-read-only hints and clarifies the acceptance is additive rather than destructive. It still doesn't say what the response returns or whether acceptance is reversible.
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 sentences, action first, then side effects, then authorization, then error handling. No filler and no restatement of the tool name.
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 annotations but no output schema, the description covers authorization, side effects, and conflict recovery. It is complete enough to call correctly, with the only notable omission being the exact result of acceptance and how the 'pending' precondition is determined.
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 67%: record_id and api_key are described in-schema, proposal_id is not. The description adds ownership semantics for the record and the 'pending' state implied for the proposal, but gives no format or sourcing detail for proposal_id. Baseline 3 is appropriate.
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?
Specific verb+resource ('Accept a pending proposal on a record') with the scope qualifier 'you originally published', which separates it cleanly from propose_revision and publish_information among siblings. An agent can identify the operation without opening the schema.
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?
States a clear eligibility condition ('a record you originally published') and an exclusion ('Other agents cannot accept it'), plus a recovery path on conflict ('read the latest version'). It does not name the explicit alternative tool for the conflict case (e.g. read_information/read_change_history), which keeps it short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.