squiggle_tips

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

Beyond the readOnly/openWorld/idempotent annotations, the description adds meaningful behavioral context. It details the return schema with all fields explained, including that 'correct is null until played,' that confidence is a percentage, and that bits is an information score. It also states 'Auth: none needed.' These disclosures go beyond the annotations. However, it does not address potential large data size beyond the round recommendation, and the 'Also answers this' line is unexplained, which could mislead. Still, it provides substantial added transparency.

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 fairly structured: a one-line purpose, a detailed return schema, an example, an auth note, and a trailing line. The purpose is front-loaded, which is good. The return schema is thorough and worth its length. However, the final 'Also answers this' sentence is vague and seems out of place, adding noise without clear value. Overall it is moderately concise but 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?

Without an output schema, the description is the sole source for return semantics, and it covers every field in the tips array, including null behavior for 'correct' and units for confidence and bits. It provides a realistic example and states authentication requirements. It also warns about round size. The only notable gap is the ambiguous 'Also answers this' statement, which could lead an agent to think this tool handles those other tools' queries without explanation. Otherwise, it is quite complete for a read-only query tool.

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?

The input schema covers all six parameters with descriptions, giving a baseline of 3. The description adds a concrete example ({'q': 'tips', 'year': 2026, 'round': 1}) that shows how to combine parameters, and it notes that round is strongly recommended to limit response size. It does not add meaning to parameters like game or source beyond the schema, but the example is useful. This is adequate but not particularly enriching.

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 opens with a clear, specific statement: 'What each model tipped for a game: winner, predicted margin, confidence %, and — for played games — whether it was right.' This names the resource (tips) and the exact data returned, and it distinguishes itself from sibling squiggle tools (teams, games, standings) by focusing on predictions. The example query reinforces the purpose without ambiguity.

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?

No explicit guidance is given on when to choose this tool over alternatives. It does not mention squiggle_teams, squiggle_games, or any sibling, and there is no 'use this when...' or 'use that instead when...' statement. The only hints are an example query and a note that round is strongly recommended, but neither helps an agent select this tool vs. others. The closing line 'Also answers this: apisports_football_predictions, datagolf_pre_tournament, datagolf_pre_tournament_archive' is confusing and does not clarify selection criteria.

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