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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered and 'Read-only' merely repeats it. The description earns credit by disclosing the returned field set (value, is_primary, status, checked_at, check_method, provenance) and decoding the status vocabulary, which goes well beyond the annotations. Auth requirements and any pagination or result limits are not mentioned.

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, then the enumerated kinds, then the return-field detail, ending on the read-only note. It is dense but each clause adds information; the long em-dash list of kinds and statuses is heavy yet justified because no schema descriptions exist.

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?

With no output schema and 0% schema description coverage, the description supplies the return shape, status semantics, and provenance fields, which is exactly what an agent needs here. Minor gaps remain around permissions and whether results can be paginated or truncated for leads with many channels.

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 0%, so the description must carry the load, and it does explain that 'kind' narrows results and lists the same eleven kinds as the enum, giving the filter's purpose real meaning. The required lead_id is never described, though its meaning is largely self-evident from the tool name.

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 ('List a lead's contact points') and enumerates the exact channel kinds covered. The closing 'Read-only' contrasts it with the mutating siblings lead_upsert_channel and lead_remove_channel, so an agent can route correctly 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?

Usage is only implied: the tool lists channels for one lead and is read-only, which suggests when to pick it over upsert/remove. There is no explicit statement of when to use it versus get_lead, get_lead_links, or list_lead_activity, and no prerequisites or exclusions.

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