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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false; the description goes well beyond them by disclosing that one scheduled notification is materialized per still-future offset server-side, that it fires with no agent running, and that each is tagged related={type:tracked_document,id:<id>}. It also explains the confirmation model (runs immediately, returns an ordinary result rather than a plan_token, undoable from the same surface) and states that destructive/outbound/financial actions still propose instead.

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 key facts (what it tracks, required fields, default offsets) are front-loaded, but the text is a dense run-on with parenthetical asides, ALL-CAPS emphasis, and marketing phrasing ('the expat killer feature'). The confirmation paragraph is long and partly restates the same immediacy point several ways, diluting scanability for an agent deciding to call it.

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 9-parameter mutation tool with no output schema and no annotation depth, the definition covers creation semantics, side effects, reminder scheduling, undo path, and confirmation behavior. Remaining gaps are minor: it does not say what the returned record contains (e.g. the generated id field name) or how duplicate titles/expiry dates are handled.

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?

With 0% schema description coverage, the description carries the load and does: it marks title and valid_until as required with a YYYY-MM-DD format, explains number_masked as last-4-only ('never the full number'), explains document_id as linking an uploaded scan in the caller's documents, and supplies a default of [90,30,7] for reminder_offsets that the schema does not encode. It slightly wastes effort re-listing the kind enum values already present in the schema, and does not constrain holder or notes beyond the schema's max lengths.

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 names a specific verb+resource ('Track a document/credential's EXPIRY and auto-schedule renewal reminders') and enumerates concrete artifact types (passports, residence permits, visas, insurances, contracts, tax deadlines). It also distinguishes itself from the sibling lifecycle tool by stating removal is done via delete_tracked_document, so an agent can separate this from update/get/delete without opening schemas.

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 context is explicit and concrete (expiry-bearing credentials and deadlines) and the description states the tool is additive and how to undo it. It does not explicitly contrast with update_tracked_document or get_tracked_document, so the when-not guidance is partial, but the create-vs-remove routing is clear.

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