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

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral facts: won/open figures exclude deals with unconfirmed attribution or a status conflict, paged results only include companies with deals, and the MCP default of 25 differs from unpaged REST behavior.

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 return payload, then exclusions, then paging behavior — a sensible order with no filler sentences. The final clause about REST calls without paging options is marginally relevant to an MCP caller but still adds a real distinction.

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, the description appropriately enumerates what comes back and how paging continues, and annotations cover the safety traits. The main omission is nesting/format guidance for the single 'query' object parameter, which is the only structured help available at 0% schema coverage.

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 effectively 0% (only limit carries text, cursor carries only a pattern), so the description must carry the load. It does explain the default page size and following pagination.next_cursor, and 'pipeline or one ICP' implies icp_id semantics, but it never clarifies that all inputs are nested under the 'query' object nor the UUID format for icp_id.

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 ('Returns per-company deal totals') and enumerates the returned measures (deal counts, won/open amounts by currency, repeat-customer flags), plus the scope choice of pipeline vs one ICP. It does not name a sibling such as listCompanyDeals to contrast with, so the differentiation is inferred rather than explicit.

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 description implies when the tool applies (pipeline-wide vs a single ICP) and notes that paged lookups only cover companies with deals, which is useful selection context. It never states when to prefer a sibling tool or a when-not condition, so the agent must infer alternatives from tool names.

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