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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the semantics of 'changed': value, eligibility, and claim-step edits, plus closed offers, and the explicit America/New_York date basis. That timezone detail materially affects interpretation of the look-back window and is not derivable from the schema. Return ordering and pagination behavior remain undisclosed.

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 that front-loads the resource and the change categories, with the window and timezone as trailing qualifiers. No filler, no repetition of the title.

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 read-only two-parameter feed with full schema coverage, annotations, and no output schema, the description covers what the tool returns conceptually (offers added/updated/closed). It stops short of describing result ordering or how the limit truncates events, which an agent consuming a change feed would benefit from knowing.

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% with defaults and min/max already documented for both parameters, so the schema carries the load. The description only reinforces the 'last N days' framing and adds the timezone context; it adds no syntax or format detail beyond that, matching the baseline 3.

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 concrete resource (offers) and the change events it surfaces (added, updated, closed) within a bounded look-back window, which is more specific than the bare name 'recently_changed'. It does not explicitly contrast itself with siblings like early_offers or get_offer, so the agent must infer the difference between a change feed and a point-in-time lookup.

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 only implied: the description makes clear this is a 'what changed lately' feed, but it never says when to prefer it over early_offers, get_offer, or find_credits, nor does it state any prerequisites or exclusions. An agent can guess the intent but gets no routing guidance.

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