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

Annotations already establish that this is a safe, idempotent, closed-world read, so the description correctly spends its budget elsewhere: it explains that totals cover the whole board even when returned rows are truncated, that amounts never add across currencies, and that without_amount and unresolved_count deals make totals a lower bound. That is unusually substantive result-semantics disclosure. It stops short of stating how row cutting/limits are controlled or what the response shape looks like.

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 purpose is front-loaded and no sentence is purely filler, but the totals passage is a dense run-on ('totals covers the whole board even when rows are cut: open and won counts and amounts by currency, which never add across currencies') with a grammatical slip that slows comprehension. Splitting the fallback-total rules into discrete statements would help.

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 carries the burden of explaining return semantics and does so well for the aggregate totals. The remaining gap is operational: nothing explains how many rows are returned, how 'rows are cut' happens, or how to page, which matters for a list tool whose totals explicitly assume truncation.

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 0% and the tool has one nested object parameter containing icp_id and visibility. The description does say deals can be listed 'optionally for selected ICPs' and covers 'active or archived', which maps loosely onto both fields, but it adds nothing about accepted formats (uuid or array up to 20), defaults, or the active/archived return difference. With nested objects and zero documented properties, the prose is too vague to compensate. Edited: this is the weakest dimension.

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 description opens with a specific verb and resource ('Lists active or archived deals with their pipeline and stages') and ties it to the question types it answers ('open deals, deal stages and what is closing'). It does not, however, name or distinguish itself from plausible siblings such as listCompanyDeals, getDealSummaries or listDealCandidates, so the agent must infer the boundary.

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?

'Useful for questions about open deals, deal stages and what is closing' gives an implied usage context, and the visibility parameter is described in prose. But there is no explicit when-to-use versus when-to-use-an-alternative guidance, and no mention of what to call instead when a per-company or aggregate-summary view is wanted.

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