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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds genuinely new behavior: the 25-lead cap, that the export lands on a real person, and the mandatory confirmation/read-back protocol. The 'reaches a real person' line largely restates the destructive annotation, so it is not a 5, but the confirmation workflow is valuable beyond the 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?

Three sentences, front-loaded with capability then constraint then safety protocol, with no filler. The repetition of 'This reaches a real person' in both the description and the confirmed field's schema description is slightly redundant but harmless.

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?

An output schema exists so return values need not be explained, and the confirmation requirement is well covered. However, for a destructive, open-world write the description omits failure/partial-success behavior, what happens if no CRM is connected, and per-lead error semantics, leaving meaningful gaps for a 7-parameter mutation.

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 description coverage is low (29%), so the description carries more burden, and it only partially compensates: it covers the 25-lead limit, the HubSpot provider, optional company association, and the optional note. It says nothing about lifecycleStage, and the note object's channel/sentAt and the leads array shape are left entirely to the schema.

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+destination ('Export up to 25 leads to a connected CRM provider') and names the supported provider (HubSpot contact upsert). An agent can tell what this does at a glance. It does not, however, distinguish itself from the confusable sibling campaignstack_add_leads_to_external_destination, so it stops short of a 5.

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, concrete precondition: tell the user exactly who it goes to, read the wording back, and wait for an explicit yes before calling. That is strong when-to-use guidance. It does not address when NOT to use this versus other lead-routing siblings (e.g. add_leads_to_external_destination), so it is not a full 5.

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