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

Annotations only declare the generic profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds real domain behavior: patches are partial, 'source is never cleared,' and relationship state moves along a defined pipeline while provenance is immutable. That is meaningful context beyond annotations, though it omits what happens if an invalid transition is requested and roughly what the result contains ('Effects: contact updated' is thin).

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 verb and the key constraint, and the pipeline notation is compact. But 'Effects: contact updated' is a tautology that burns a sentence, and the bare reference 'JH-2' is unexplained jargon an agent cannot resolve.

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?

No output schema exists, so the description should at least hint at what comes back and what happens on failure; 'contact updated' is too vague, and illegal-transition behavior is unstated. It does cover the mutation's safety-relevant constraints, which keeps it from being inadequate for a 9-parameter write tool.

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 low (22%), so the description must carry weight. It does explain the two genuinely tricky fields — the relationship enum's allowed progression (cold → contacted → responsive → warm_scout, or dead) and the source field's correctable-but-not-removable rule — but leaves name, role, email, notes, phone, and linkedin_url completely undescribed, including whether empty values clear a field.

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?

Specific verb+resource ('Patch a contact') that is clearly distinct from hunt_add_contact and hunt_get_contact by the update operation. However, it never distinguishes itself from the near-identical sibling crm_update_contact, which an agent has no basis to choose between from this description alone.

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?

The 'Patch' framing implies partial-update usage and the mention that relationships can transition while provenance cannot gives some context on legitimate use. But there is no explicit when-to-use, when-not-to-use, or reference to alternatives such as crm_update_contact or hunt_correct_application, so the agent must infer.

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