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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context the annotations cannot convey: outcome is null until minCohort tippers have picked, and the expert cohort is weighted by Weltrang ranking.

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?

Three tight sentences: what you get, how to scope the call, and the one edge-case caveat. Front-loaded with the payload description and no wasted framing.

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 return-value burden and largely discharges it by naming the three output components and the null-outcome condition. It could still note pagination or ordering for the list form, but nothing critical is missing.

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% and both enums (mode, status) are self-documented, so the schema already does the heavy lifting. The description adds only the concrete id format example, which is mildly helpful but largely restates the schema's filter semantics.

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 verb+resource (get the crowd consensus) and enumerates exactly what is returned: 1X2 shares, top-3 exact scorelines, and a Weltrang-weighted expert cohort. It stops short of explicitly distinguishing itself from get_crowd_record, so an agent must infer the boundary from the sibling's name alone.

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 tells the agent how to select scope: pass an id for a single match, or mode/status filters for a list. That is real routing guidance, but it never says when to prefer this over get_crowd_record or list_matches, nor any exclusions or prerequisites.

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