Refresh taxonomy snapshots

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false. The description adds real context beyond them: nothing is written by default, writes are gated behind a successful dry run, and live write should only happen when write proof is needed.

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 sentences, front-loaded with what is built, then the safe default, then the condition for going live. Every sentence carries distinct information with no repetition.

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 zero-required-param, mutation-capable tool with no output schema, the description covers purpose, default safety posture, and the write gate. It doesn't describe what a snapshot contains or what the dry-run output looks like, which would help an agent validate results.

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 100%, so the baseline is 3. The description reinforces the dry_run default and its safety meaning, but says nothing about max_sources, max_snapshots, or max_sources_per_snapshot beyond what the schema already states.

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 ("Builds") plus a distinctive resource ("source-linked Memory Library taxonomy snapshots") and names its inputs ("active facts and sessions"). An agent can identify what it produces without opening the schema, though it doesn't explicitly contrast with storage siblings like save_fact or workspace_put.

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?

Gives an explicit gating rule for the critical choice: it defaults to dry run and "Only pass dry_run=false after the dry-run output is safe and the job needs live write proof." That is a clear when-to-use condition, but no alternative tools or escalation path are named.

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