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

Annotations already cover the safety profile (non-destructive, idempotent, closed-world), and the description adds genuinely new behavior: overwrite-on-name-collision, per-call cost of $0.001 with no charge on failure, and that relative dates like today+30 are re-evaluated on every use. It stops short of saying whether a replace also overwrites `sort`/`object` or what is returned.

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?

One dense paragraph, front-loaded with the core action and semantics before the downstream-usage and cost clauses. Every sentence carries information, though the cost/failure clause and the parenthetical could be tightened slightly.

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 4-parameter, non-destructive upsert tool with no output schema, the description covers purpose, upsert behavior, consumers, date semantics and cost. Remaining gaps are minor: the returned identifier and the fate of `sort`/`object` on overwrite are unspecified.

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 50%: `filters` is documented richly in the schema, while `name`, `object` and `sort` are bare. The description compensates partly by giving a segment-name example and by explaining that relative date expressions in filter values are resolved at use time, but it says nothing about `object` scoping or `sort`, so the gap is only partially filled.

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 specific verb+resource ("Save filters under a name") and immediately clarifies the upsert semantics: a new name creates a segment, an existing one replaces its filters. The concrete example ("customers renewing within 30 days") makes the resource unambiguous and distinguishes it from crm_list_segments/crm_delete_segment.

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?

Explicitly tells the agent where the saved segment is consumed: the `segment` argument of crm_find_contacts, crm_find_companies, crm_find_deals and crm_export. That is strong downstream context, but it does not say when *not* to save a segment or point to crm_list_segments/crm_delete_segment for the alternative workflows.

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