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

Adds substantial behavior beyond the annotations: partial-update semantics ('only the fields given change'), the empty-string-clears convention, the replace-not-append semantics of tags, and the duplicate-email/phone refusal that returns the existing contact's id. These are exactly the non-obvious behaviors an agent would otherwise discover by trial and error.

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 dense sentences, front-loaded with the add/edit distinction, then the update semantics, then the tag caveat and the failure case. No filler, no restatement of the tool name.

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 14-parameter upsert with no output schema, the description covers the critical decision points: mode selection, partial update, field clearing, tag replacement, and duplicate rejection. It omits what the call returns and whether any permission/account context is required, but nothing stated is misleading.

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 only 7% (14 params, one documented), so the description carries a heavy burden and does add real meaning: partial-update behavior applies to every field, empty string clears a value, and tags replaces rather than merges. It still says nothing about the many undeclared fields (source, company, name vs first_name/last_name, phone formatting), leaving most parameters semantically undefined.

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 pair and distinguishes the two operating modes ('Add a new CRM contact, or edit one by contact_id') in the first clause. It also names the sibling crm_tag_contacts for the tag-modification case, so an agent can separate it from related CRM writes 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?

Explicitly routes tag add/remove work to crm_tag_contacts, which is the main sibling-confusion risk for a contact-write tool. However, it gives no guidance on choosing between this and other CRM write siblings such as crm_update_pipeline-style helpers, and no prerequisites are mentioned.

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