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

Goes well past the annotations: discloses per-call cost ($0.01), that failures are free, case-insensitive name matching, additive tag behavior, and merge/null-clear semantics for custom fields. These are exactly the traits (billing, merge-vs-replace) annotations cannot convey and that drive correct invocation.

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, front-loaded with the create-or-update decision, then the id override, then mutation/billing semantics. No filler; every clause adds a decision-relevant fact.

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?

Covers matching, partial updates, merge behavior and cost for a 10-param nested-object tool with no output schema. The one gap is what comes back (the created/updated company id and whether an insert or update occurred), which matters for chaining calls since no output schema documents 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?

With only 30% schema coverage across 10 params, the description carries real weight: it defines name's dual role (required-to-create vs new-name-on-update), company_id's overriding behavior, and the merge semantics of tags and custom_fields. The remaining six params (notes, domain, website, industry, employee_count, lifecycle_stage) are left to their types/enum, which are self-explanatory but undocumented.

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?

A specific verb and resource with the upsert contract spelled out: create, or update the case-insensitive name match, or update/rename by company_id. An agent can tell exactly what record is touched without opening the 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?

Gives clear selection rules between the name path and the company_id path, plus the partial-update rule ('only the fields you send change'), which is the key usage context. It does not name alternatives such as crm_save_companies (bulk) or crm_merge_companies, leaving that routing to inference.

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