get_activity

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

With no annotations, the description carries the burden. It discloses ordering ('newest first'), pagination behavior ('paginate with the returned cursor'), and authentication ('Requires a developer key'). These are useful behavioral traits beyond the schema. It lacks rate limits or error behavior, but still provides substantial transparency.

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?

Two sentences, front-loaded with purpose, then filters, then auth. Every clause delivers value; no filler or redundancy.

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?

Despite no output schema, the description covers feed scope, ordering, filtering, pagination, and authentication—enough to select and invoke the tool correctly. It omits the response shape, but 'feed' and the listed event types give a reasonable mental model. The complexity is moderate (6 optional params), and the description addresses all major usage aspects.

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 baseline is 3. The description adds a high-level summary of filters ('Filter by agent, type, or time range') but no new parameter-level detail beyond what the schema already explains for type, limit, since, until, cursor, and agent_id. The cursor description is already in 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?

The description begins with 'Unified account activity feed' and enumerates the event categories (x402 proxy calls, onramps, transfers, loan events), clearly distinguishing it from siblings like get_balances and get_usage_summary. It states the resource and scope with a specific verb implied by 'get_activity'.

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?

It explains filtering by agent, type, or time range and explicitly mentions pagination via the returned cursor. It also notes the developer key requirement. It does not contrast with alternatives explicitly, but the feed description implies use for listing activity events, and no sibling offers this unified view.

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