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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: opening a snippet returns raw text plus signed attachment URLs, and other modes expose queues/outcomes/implementation context. It does not detail pagination or per-mode side-effect warnings, but for a read-only tool the important behaviors are stated.

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?

Two sentences, no filler. The most decision-relevant behavior (snippet:// returns text and signed URLs) is front-loaded, and the second sentence orients the agent to the mode families without enumerating all 24 modes.

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 very complex tool (29 parameters, 24 modes, no output schema), the description is thin but the schema carries essentially all parameter semantics and the annotations carry the safety profile. The description adds the missing top-level map of what the modes do. A fully complete description would name a few high-usage modes and mention pagination, so this is not 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%, so the schema fully documents all 29 parameters, including enums and references. The description adds only a light interpretive gloss ('Other modes expose queues, outcomes and implementation context') and the snippet:// behavior. That is useful but does not materially clarify individual parameters; baseline 3 is appropriate.

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 verb ('Find or open'), a concrete resource ('Atisbo entities'), and immediately gives a distinguishing behavior ('opening snippet:// returns its text and signed attachment URLs') plus a high-level inventory of alternative modes. This differentiates it from the sibling tools and from the other modes within the oversized enum.

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 states when to use the tool (finding/opening entities) and broadly separates read-style lookups from other modes ('Other modes expose queues, outcomes and implementation context'). It does not explicitly name sibling alternatives and exclude them, but the sibling names (atisbo_capture, atisbo_decide, etc.) make the predicate evident. The lack of an explicit 'use X for mutations' statement keeps it from a 5.

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