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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description goes beyond annotations by disclosing ordering behavior (soonest remind_at first, undated last), consent-gating for team scope, attribution to owner, and the read-only nature in words. This adds meaningful behavioral context without contradicting the annotations.

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?

The description is dense but every clause earns its place: the core sweep behavior is front-loaded, followed by scoping and filtering variants. It is slightly long for a single paragraph, but each sentence contributes a distinct piece of usage or behavioral guidance, so the length is justified.

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 read-only list tool with six optional parameters and an output schema already provided, the description covers the key contexts: whole-network sweeping, team consent gating, goal-based filtering, undated filtering, per-person scoping, and limit capping. Edge cases like team_id being required when multiple teams exist and Goal ownership for team sweeps are addressed, making it complete without needing to describe the return value schema.

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 baseline is 3, but the description adds real semantics beyond the schema: it explains that scope:'team' returns consent-gated open actions attributed to their owner, that team_id is needed only when you belong to more than one team, that a team sweep requires a Goal owned by the selected Team, and that undated:true isolates open-ended follow-ups. These enrich the parameter meanings beyond the bare field descriptions.

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 and resource: lists OPEN follow-up/actions across the whole network in one call, with each action attached to its person. It distinguishes itself from the per-person get_person approach and, among siblings, is clearly the aggregation read call rather than create_action, update_action, complete_action, or delete_action.

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 description gives explicit when-to-use guidance: "Use this to sweep all your to-dos... instead of calling get_person per person." It also provides the exclusion condition: "for one person's actions use get_person → relationship.actions." It further clarifies team scope prerequisites, goal ownership constraints, and filtering options, leaving no ambiguity about when to select this tool.

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