record_decision

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

No annotations are provided, so the description carries the full behavioral burden. "Log" implies a write, but nothing is said about persistence, duplicate handling, required auth (an api_key parameter exists but is unexplained), or what happens to the aliases. Only a hint of downstream behavior (later retrieval via why()) is disclosed.

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?

A single dense sentence with the core action front-loaded and no filler. It is compact, though the alias-heavy phrasing slightly increases parsing effort for an agent.

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 13-parameter write tool with no annotations and no output schema, the description is too thin: it omits meaning for most parameters, says nothing about auth/credentials, required inputs, or return values. An agent can call it but not confidently populate the 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?

Schema description coverage is 0% with 13 parameters, so the description must compensate. It names only 5 concepts (what/decision, why/rationale, related_ids) and helpfully documents the alias pairs, but 8 parameters (tags, agent, api_key, project, entities, evidence, session_id, alternatives) are completely undocumented in both schema and description.

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 ("Log a decision") and the key payload fields (rationale, related_ids). It also ties the tool to the sibling `why` by explaining the downstream use ("so other AIs can later ask why()"), giving partial sibling differentiation, though it does not contrast with `remember`, `observe_preference`, or `add_leftover`.

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?

Usage is implied rather than stated: the reader infers they should call this when they want a decision retrievable later via why(), and the linking instruction ("Link code/memory ids via related_ids") gives a concrete action. There is no explicit when-to-use vs when-not, and no mention of the other recording siblings as alternatives.

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