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

Annotations already cover the read-only safety profile, and the description adds real value beyond them: it discloses the transport endpoint and, crucially, the return shape { list, next_cursor } despite there being no output schema. What's missing is pagination termination behavior and whether limit caps server-side results beyond the schema's 5000 ceiling.

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?

Three short sentences: purpose, endpoint, return shape. Every element earns its place and the purpose is front-loaded. 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?

With six optional filter parameters, the description adequately frames the tool: filters are enumerable from the schema, the return envelope is disclosed, and cursor semantics are mentioned. Without an output schema it carries the return-shape burden well, though it could say more about total counts or empty-list behavior.

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 limit, search, plans, processors, start_cursor, and subscription_status are all documented in the schema itself. The description only adds the generic framing 'cursor pagination' and doesn't clarify ambiguous cases like the plans object shape or the default-both subscription_status behavior. Baseline 3 applies.

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 gives a specific verb and resource ('List/filter customers') plus the backing endpoint (POST /v1/customers.list), which makes the operation unambiguous and distinguishes it from get_customer. It stops short of naming siblings explicitly, so it lands just below the top of the scale.

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?

The word 'filter' signals the tool's role, and the pagination note implies repeated-call usage, but nothing states when to prefer this over autumn_get_customer (single lookup) or autumn_list_entities. Usage must be inferred from the tool name and sibling set.

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