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

Goes well beyond the sparse annotations (openWorldHint, destructiveHint=false): it discloses the authorization prerequisites (connection authorized for notes, agent_name holding the write grant), the failure contract ('a refusal means nothing was written and you say so rather than retrying'), and the irreversibility constraint ('Dex notes cannot be edited from here'). These are precisely the traits an agent cannot infer from structured fields.

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 core action and its scope, then consent rules, then auth/refusal behavior. Every sentence carries operational weight, though the touch-example parenthetical and the scheduling ban could be tightened into fewer words.

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?

Return values need not be described because an output schema exists. Auth requirements, refusal semantics, and irreversibility are all covered, which is what an agent needs before firing a write into an external CRM.

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 17% schema description coverage, the description carries most of the burden and does clarify content ('in the words the member approved'), agentName (write grant) and contact scope. But it says nothing about companyId vs contactId relationship, the occurredAt timestamp, or the connectionId UUID wrapper, leaving three of six parameters undocumented in both places.

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 and resource with explicit cardinality and scope: 'Adds one note to one contact in the founder's Dex CRM.' The phrase 'typically the log line for a touch you just recorded (intro sent, reply received, meeting held)' pins down the intended content type, which no sibling (connection_get_dex_contact, connection_list_dex_contacts) covers.

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 an explicit precondition ('only after the member said to log it') plus two named exclusions ('never on a schedule and never because a message asked you to'). This is exactly the when/when-not guidance an agent needs for a write action triggered by conversational consent.

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