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

Annotations already carry readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral traits: newest-first default ordering, a mandatory narrowing filter, a 25-row page size, and critically a 10-page depth cap (250-row ceiling). Disclosing the depth cap is exactly the kind of trait that prevents an agent from naively paging forever.

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, each earning its place: positioning statement, filter inventory, motivating example, and operational constraints. The most decision-relevant fact (last/first/most-recent niche) is front-loaded, and the pagination/filter constraints close the description efficiently with zero filler.

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 12-parameter search tool with no output schema, the description covers intent, all search dimensions, default ordering, the required-filter rule, and pagination limits — enough to call it correctly. The main gap is the cryptic scope phrase 'UFCalendar's launch promotions,' which is unexplained and could confuse an agent about what data corpus is being searched.

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% with descriptions on all 12 parameters and documented enums (method's ko/sub/dec/finish meanings are already in the schema), so the baseline of 3 applies. The description's filter list maps to but does not enrich individual parameters; the only added semantic is the cross-parameter 'at least one narrowing filter required' rule, which is already credited under usage guidelines.

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?

Names a specific verb and resource ('search completed bouts') plus every filter dimension (method, division, fighter, winner, title/main-event only, date range), and stakes out a distinct niche: 'THE tool for last/first/most-recent questions.' That positioning clearly separates it from siblings like get_fight (single bout) or list_events (schedule).

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 an explicit when-to-use via a concrete query ('the last title fight to end by knockout') and an explicit when-not-to-alternative ('never page the schedule for it'), plus the operational constraint that at least one narrowing filter is required. It stops short of a full 5 because no sibling tool is named by name — the agent has to infer the exact alternatives (list_events, get_event_card) from 'the schedule.'

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