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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuinely new behavioral context: results can contain failed/unknown constraints that must be preserved, and admission subtotals are estimates rather than checkout prices. It does not cover what happens on cross-city IDs or how partial failures are surfaced, but the added output-handling guidance is substantive.

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 short sentences with the scoping rule front-loaded, then output-handling caveats. Terse to the point of being telegraphic ("Preserve failed and unknown constraints" lacks a subject), but nothing is padding.

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 tool with four parameters, two of them nested objects, zero schema descriptions and no output schema, the description leaves too much unsaid. Price semantics and unknown-data handling are covered, but an agent cannot tell from this text what party or filters do or how filtering affects the comparison, which is a material gap given the complexity.

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 0%, so the description must carry all parameter meaning, yet it only restates the ids cardinality (already enforced by minItems/maxItems) and adds the same-city rule the schema cannot express. The two nested objects — party (adults, child_ages, ticket_category) and filters (indoor, stroller, max_admission_usd, all_children_suitable) — are never mentioned, leaving their purpose and interaction entirely unexplained.

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?

Specific verb+resource ("Compare 2-4 IDs") with scope constraints (same city), which is far more than the title restates. It only implicitly points at the sibling that produces the IDs ("returned by search") rather than naming search_family_activities, and never differentiates itself from plan_family_outing or get_activity_details.

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?

Gives a clear precondition and workflow position: the IDs must come from a prior search and must share a city, so the agent knows this is a second-step tool. It stops short of stating when to prefer comparing over fetching details for one ID, or when to hand off to plan_family_outing.

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