Save my identity

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

Goes well beyond the annotations by stating the stored data is "non-authoritative," "loads as reference context," and "never proves human provenance and cannot authorize or govern a future session" — a real trust/authority caveat an agent would not infer from readOnlyHint=false/idempotentHint=true. It leaves the upsert-by-key semantics implied by "saves or updates" rather than stated, keeping it just short of a 5.

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?

Front-loaded with purpose, then usage, then exclusions — the ordering is correct. The middle trigger-phrase list is long and somewhat redundant with the surrounding rules, costing some tightness, but every clause still conveys a distinct rule.

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 non-destructive, idempotent write with full schema coverage and no output schema, the description covers purpose, boundaries, and authority caveats. The only meaningful gap is the absence of guidance on category selection or priority behavior across sessions.

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 100%, so key, value, category enum, and priority are already documented. The description's phrase lists map loosely to what belongs in an entry but add no guidance on choosing a category, priority ordering, or key naming beyond the schema.

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?

Opens with a specific verb+resource and scope: "Saves or updates a non-authoritative identity or preference proposal that loads as reference context." It explicitly distinguishes itself from the closest sibling (save_fact) in the same paragraph, so an agent can route without opening either 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?

Gives explicit trigger phrases, an explicit exclusion ("Do NOT trigger for one-time facts about a specific task or project (use save_fact instead)") and a second exclusion for user-flagged temporary information. When-to-use, when-not-to-use, and the alternative are all present.

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