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

Annotations already declare readOnly/idempotent/non-destructive, so the margin is in what the description adds: the boundary rule that 'a value exactly on a limit belongs to the next level' and that Vora supplies no defaults. That is genuinely useful interpretation context an agent could otherwise get wrong. It does not cover empty-result behavior or ordering, which keeps it below a 5.

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 resource and scope, then threshold semantics, then the no-slug case — a sensible order. The inline GKI example earns its place by making the exclusive-boundary rule concrete, though the parenthetical is slightly dense for a single sentence.

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?

There is no output schema, and the description compensates by enumerating the returned fields — color, from/upTo, optional label, date set — plus the threshold interpretation rule. For a one-parameter read tool, an agent has everything needed to call it and read the result correctly.

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 coverage is 100%, so the slug parameter is already documented. The description nonetheless adds meaning the schema lacks: omitting slug returns every biomarker that has levels, which tells the agent the parameter is optional in effect and what the fallback scope is.

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 resource and scope: 'the signed-in user's own traffic-light levels per biomarker', making clear this is a read of the caller's own thresholds rather than a global or suggested set. The qualifier 'as set by the user; Vora suggests none' separates it cleanly from any advisory or mutation sibling such as vora_set_traffic_light or vora_delete_traffic_light.

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 final sentence 'Without slug: every biomarker that has levels' gives concrete invocation guidance for the optional-filter case. It implicitly contrasts with the write siblings by being the only non-mutating reader of these levels, but it never explicitly says when to prefer this over vora_get_latest_biomarkers or vora_list_biomarkers.

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