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

Annotations already cover read-only and open-world behavior, and the description adds genuinely useful context beyond them: the unfiltered source exceeds ten thousand rows, so the agent knows to filter or expect a large payload, and blank source tiers map to 'unrated'. It stops short of describing pagination or truncation behavior for that large result set.

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 sentences, front-loaded with what is returned, then the follow-up routing, then filter semantics and payload size. Every sentence carries information an agent needs and nothing is padded.

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?

With an output schema present, the description does not need to explain return values, and it still names the key fields. For a single optional-parameter directory tool with annotations covering safety, the description covers volume, filter semantics, and downstream usage — nothing essential 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% and the schema already lists all five tier values including the blank-tier mapping, so the description largely restates it. The only added nuance is that tier matching is 'exact', which is a small but real clarification; baseline 3 applies when the schema does the heavy lifting.

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 and resource ('Returns OpenDota's complete league directory') and enumerates the returned fields (league IDs, names, tier, ticket, banner metadata). It clarifies scope versus the match-oriented siblings by pointing to opendota_league_matches, but never distinguishes itself from the singular opendota_league or opendota_league_match_ids tools.

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?

Explicitly routes the agent forward ('Use a returned league_id with opendota_league_matches') and explains the tier filter's role and accepted values. It gives clear context for use but states no exclusions or when-not conditions (e.g., when a single league lookup would be preferable).

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