commitment_ingest

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so richly. It reveals that nothing is deleted (states-not-deletions), only the fact is stored while body/notes/location are dropped, and that cancel/reschedule events become proposals routed through a SAFE gate—all beyond what a simple schema could convey.

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 description is well-organized and front-loaded with the core purpose, then elaborates on behavioral rules, parameter semantics, and restrictions. Every sentence adds necessary context, and the length is justified by the tool's complexity.

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?

The description covers nearly all necessary aspects: main function, persistence target, state transitions, error condition, and the important restriction against calendar write-back. The only noticeable gap is the lack of information about the success return value, which is not covered by an output 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?

The description adds substantial semantics for the 'events' parameter, detailing its structure (uid/title/start/end/attendees/body/cancelled) and the ISO-8601 format, as well as behavior when omitted. However, the required 'app_id' parameter is not explained at all, leaving its meaning and format ambiguous despite being required.

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?

The description clearly states a specific verb ('ingest') and resource ('calendar events into the operator's commitment ledger'), and further specifies persistence to a named collection. It distinguishes itself from sibling tools by detailing its unique state-transition model (ACTIVE/WITHDRAWN) and its read-only relationship with the calendar source.

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?

The description gives clear usage context: when to push events explicitly vs. omit to pull from a live calendar source, and mentions the resulting 'transport_unwired' error if the transport isn't wired. It also explicitly states that it never writes back to the calendar and that write-back goes through a SAFE gate not exposed over MCP, which implies when not to use this tool, though it does not name alternative tools.

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