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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond that, specifically 'Pure computation, $0 cost' and the data sources used. It stops short of disclosing accuracy, confidence, or prediction limits.

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?

Four sentences, front-loaded with the purpose, then data sources, return values, cost, and audience. The return-value sentence is somewhat redundant because an output schema exists, but the description remains efficient and every other sentence earns its place.

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 complex prediction tool, the description covers purpose, data sources, outputs, cost, and audience, while annotations cover safety and the output schema covers return structure. Nothing essential for correct invocation 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 description coverage is 100%, so the schema fully documents ticker, year, and resolution_type. The description adds no parameter-level meaning beyond implying an NZX company ticker and resolution scope. Baseline 3 is appropriate when structured schema already carries parameter 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 ('Predict') and resource ('outcome of AGM resolutions for an NZX company'), and distinguishes itself from retrieval siblings by calling itself 'Pure computation' and naming prediction outputs like 'predicted support %, swing voters'. An agent can tell what it does without opening the 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?

Names target users ('proxy advisors, companies planning contentious resolutions, and institutional investors'), which implies a usage context. However, it never explicitly says when to choose this tool over alternatives such as get_vote_history or get_agm_resolutions, and there are no exclusions or prerequisites.

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