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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so 'Read-only' restates structured data rather than adding to it. The description does add genuine behavioral content by spelling out which signals raise a pair (email, LinkedIn, phone, name containment, shared organization) and that both values plus any reviewer recommendation are returned, but it omits pagination, result limits, and whether entries can be filtered by review status.

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?

A single front-loaded sentence opens with the key framing ('The dedup queue') before elaborating, and the parenthetical signal list is informative rather than filler. It is dense but every clause contributes; only the terminal 'Read-only' is redundant with annotations.

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?

An output schema exists, so the description needn't document return structure, and annotations cover the safety profile; what it does provide is the semantics of the payload (what a pair is, what signals and values it includes). The remaining gap is operational — no mention of paging, ordering, or the follow-up tools for acting on a duplicate — which keeps it short of a 5.

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% for the single companyId parameter (a UUID value wrapper), so the schema already carries the semantics and the description adds nothing about it. Baseline 3 applies since there is no low-coverage gap to compensate for.

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 names a specific resource ('the dedup queue: pairs of network people that look like one person') and enumerates what each pair carries, so an agent knows exactly what comes back. It does not, however, distinguish itself from nearby siblings such as fundraising_scan_network_duplicates, fundraising_list_network_merges, or fundraising_list_network_people, leaving the agent to 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?

Usage is only implied: describing the output as 'the dedup queue' suggests this is a read-side companion to scanning/merging tools, but no explicit when-to-use, when-not-to-use, or named alternative appears. The trailing 'Read-only' signals safe inspection but is not guidance about selection.

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