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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so safety is covered. Beyond that, the description discloses default page size of 25 compact companies, cursor-based continuation, that stage_counts is null when unreadable, that pipeline_scope saved without icp_id reads every ICP, and that non-paged REST calls keep the full snapshot. Only the 'compact' payload shape is left somewhat undefined.

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?

The scope statement and pagination behavior are front-loaded, and nearly every semicolon-delimited clause adds a distinct operational fact. The density and semicolon chaining make it slightly harder to scan than a bulleted structure would, but there is little filler to cut.

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 tool with a nested conditional query object, no output schema and no required parameters, the description covers pagination, count semantics, per-stage filtering, single-account lookup, projection choice and the REST fallback. An agent has enough to call it correctly in every documented mode.

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?

Reported schema coverage is 0%, so the description has to carry parameter meaning, and it mostly does: stage is keyed by name as it appears in stage_counts, company accepts a name fragment or domain without '*', card_id pairs with projection full, and the icp_id/pipeline_scope interaction is spelled out. The limit and cursor parameters are only referenced obliquely via 'follow pagination.next_cursor'.

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?

The opening clause names the resource precisely: companies grouped by pipeline stage, each with its contacts, constrained to the selected ICP scope. That is enough to separate it from listPipelineContacts or getPipelineConfiguration without opening the schema, though the description never names a sibling explicitly.

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?

It routes the agent for every mode: use stage_counts for counts and 'never page through cards', pass stage with a name to list one stage, pass company with a partial name or domain to locate an account, and use card_id with projection full for a single company's details. Each alternative comes with the condition that selects it.

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