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

Goes well beyond annotations: discloses auth scope (api:account), plan-limit behavior (403 tier_limit_exceeded), refusal codes (422 mandate_rule_violation with reason codes like active_mandate_immutable), the immutability of active/paused mandates, API-key restrictions on higher autonomy levels, and the return payload (saved Gambit plus app_url). It also clarifies no trade is placed, which matters given sibling trade tools.

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?

Dense but front-loaded: the core purpose and action-dispatch lead, with edge rules trailing. Given 5 actions and 13 params, most sentences earn their place, though the lifecycle/error-detail run-on in the middle could be tightened.

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 return fields and app_url. Combined with lifecycle rules, error codes, auth scope, and limit behavior, an agent has everything needed to invoke correctly across all five actions.

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 54% schema coverage and 13 params, the description compensates well: it maps text→refine, terms→compile_scope, title+mandate_text→create, mandate_id→update/supersede, explains the status transition matrix, restricts autonomy_level to 0-3, and notes monitor_interval_minutes is editable anytime. A few params (metadata, starts_at, expires_at, policy_delta) remain uncovered in both description and schema, so not a full 5.

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 set and resource: 'Create, edit, pause or refine one of YOUR saved Gambits (mandates...)'. It names the dispatch mechanism ('Pick the action'), enumerates each action's meaning, and differentiates itself from delete_mandate and the read siblings (get_mandate, list_mandates). An agent can distinguish this tool from create_gambit/get_mandate without opening schemas.

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?

Explicit when/when-not guidance for every action: create for new content, update for drafts, supersede when the target is active/paused, refine to turn loose intent into wording (nothing saved), compile_scope to preview term resolution. It routes deletion to delete_mandate and describes the draft→active→paused lifecycle, so selection is unambiguous.

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