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

Annotations only declare readOnlyHint=false, so the description carries the burden and does it well: it discloses the success outcome (YES WITH EVIDENCE plus a receipt), the failure path (refused with instructions), the return artifact (handoff_code), and a key behavioral caveat that the check is pattern-based, not semantic, and can miss paraphrases. That caveat is exactly the kind of non-obvious trait that prevents misinvocation.

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 mode/scope and the required format, then the output and the pattern-matching caveat. Slightly redundant in restating the acceptance outcome ('Accepted -> YES WITH EVIDENCE + a receipt' and 'Accepted memos return a short handoff_code'), but every element is load-bearing and there is no filler.

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?

No output schema exists, and the description supplies the return semantics (YES WITH EVIDENCE, receipt, handoff_code) plus the refusal behavior and format constraints. Combined with the 80%-documented schema, an agent has everything needed to invoke it and interpret the result.

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?

With 80% schema coverage the baseline is 3, but the description adds real meaning: the label vocabulary is tied to specific facts ([KNOWN]=survey 31.2%, [INFERRED]=forecast 2.1%, [CONFLICTED]=panel_b 0.4%) and 'cites facts by key (survey, forecast, panel_b)' clarifies what the cites array should contain. The one-label-per-number rule is reinforced with a worked example, going beyond the schema text.

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?

Specific verb (submit) plus resource (internal memo) scoped to 'Practice mode, Consumer Pulse copy only', with the cited facts named (survey, forecast, panel_b). An agent can distinguish this from siblings like atlas.pulse_use or atlas.submit_evidence without opening any schema.

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?

Clearly states the gating context: practice mode only, restricted to Consumer Pulse copies, and cites-by-key semantics. It does not name an alternative tool for real/non-practice work (e.g., a sibling that handles live memos), so the routing guidance stops short of explicit when-not/alternatives.

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