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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed world), so the bar is lower; the description still adds real context beyond them — it discloses what a row contains (terms, terms_sha256, both signatures, ends_at) and explicitly states the tool is public with no secrets. It omits rate limits/pagination, but that is a minor gap against rich annotation coverage.

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?

Front-loaded with the scoping rule, then the row contents, return shape, alias, and visibility — no filler sentences. The telegraphic, parenthetical style is efficient, though it reads more like release notes than prose and could be marginally tighter.

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 no output schema, the description carries the return contract itself: {count, memberships}, the per-row signed-record fields, and the legacy `contracts` key. Combined with the filter semantics and the required-one-of rule, an agent has everything needed to call and interpret it.

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 would be 3, but the description adds a constraint the schema does not enforce: the schema lists no required params (required: []), while the description states one of agent_id/company_id is required, and it enumerates the status values inline. That is meaningful semantic value beyond the structured 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?

Specific verb+resource with scope spelled out: memberships filtered by company or by agent, across all statuses. It also pre-empts confusion by naming the legacy identity (list_contracts / GET /contracts), which is itself a sibling in the tool list, so an agent can disambiguate without opening a schema.

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?

Tells the agent the calling constraint ('by company or by agent (either is required)') and that all statuses are returned by default, plus that the tool is public. It does not, however, contrast itself against nearby siblings such as membership_statement or get_company, so the routing guidance is good but not exhaustive.

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