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

Annotations already declare the mutation profile (readOnly=false, idempotent=false, destructive=false), so the bar is lower, yet the description adds a genuinely non-obvious trait: duplicate detection runs asynchronously minutes later, and the caller must re-read detected_duplicates. It omits what happens on validation failure or whether retries create extra leads.

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?

Four short sentences, front-loaded with the core action, then ordering caveat, then the dedup caveat, then the endpoint. Every sentence carries information the agent needs; nothing is filler.

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 two-parameter create tool with no output schema, the key operational facts (where column keys come from, deferred dedup, no outbound message) are all present. Minor gap: it never states what is returned (presumably the created lead) or which columns are required by a given list.

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 100% and both parameters are documented in-schema, so baseline 3 applies. The description's note that `fields` keys are list column keys largely repeats the schema's own wording, adding no syntax or type guidance for the nested object beyond what's already given.

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 ("Add a new lead to a list") plus the REST endpoint, which makes it unambiguously distinct from myphoner_update_lead, myphoner_create_list, and myphoner_move_lead. An agent can select it without opening the 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?

Points at the prerequisite sibling (myphoner_list_columns) for obtaining valid column keys, and the line "Creates data only; nothing is sent to the lead" separates it from outreach-style siblings like delegate_lead. It stops short of an explicit "use update_lead instead when the lead already exists" exclusion.

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