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

Annotations already declare this is a non-read-only, idempotent, non-destructive local write; the description goes further by disclosing the side effect of persist_identity=true (Cairn credential written to private local storage) and the practical consequence (identity persists across restarts). It does not contradict the annotations, and the 'grants nothing' warning clarifies that this records rather than authorizes. It stops short of describing failure behavior or what a re-record does to previously stored values beyond 'change or narrow'.

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?

Four dense sentences, each carrying distinct information (purpose, prohibition, side effect, mutation/stop semantics), with the most critical safety warning front-loaded after the purpose. Slightly run-on in the parenthetical clause, but nothing is filler.

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 4-parameter local write with no output schema and full schema coverage, the description supplies everything needed to call it correctly: the precondition, the storage side effect, the reversibility path, and the scope constraint. No output-schema explanation is required since none exists.

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, but the description adds real meaning: persist_identity=true is explained as storing the Cairn-only credential needed to keep the same participant across restarts, and mode this_action is framed as the switch that disables automatic contributions. These go beyond the schema's own wording for those fields.

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 precise verb+resource: recording a permission the user has already granted, with the explicit scoping clause 'so later visits can search and contribute without asking again'. The 'This tool grants nothing' line sharply separates it from any tool that would itself request or perform the action, so an agent can distinguish it from siblings like cairn_a2a_contribute.

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 precondition ('never call it before the user answers'), a re-entry rule ('Re-record to change or narrow it'), and a stop condition ('pass mode this_action to stop automatic contributions'). When-to-call, when-not-to-call, and how-to-reverse are all covered.

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