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

The description discloses several behavioral details beyond the annotations: 'query window capped at 365 days', 'Immutable past data', 'empty range no-charges', 'Costs 2 credits ($0.04 USDC)', and 'Requires Authorization: Bearer tf_live_<64-char-hex>'. These cover cost, auth, data immutability, and parameter constraints, providing significant context beyond readOnlyHint/openWorldHint/idempotentHint.

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 three sentences, front-loaded with the primary purpose, and packs all necessary details (parameters, cap, cost, auth, alternative) without fluff. Every sentence adds value.

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?

The description covers purpose, parameters, time bounds, cap, cost, auth, and a pointer for feed ids. It does not describe the output structure (no output schema exists), and the implied requirement for feed contradicts the schema's optionality. For a paid tool with 3 params and no output schema, this is nearly complete but leaves minor gaps around response format and parameter requiredness.

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 descriptions already cover each parameter (feed, from, to) with format examples. The description adds a query-window cap ('capped at 365 days') and billing nuance ('empty range no-charges'), which go beyond the schema. However, it implies feed is required ('for one feed') while the schema's required list is empty, creating slight ambiguity about whether feed can be omitted.

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 uses a specific verb and resource: 'Returns the daily composite-reliability time-series for one feed' with an example feed. This clearly distinguishes it from the sibling tf_premium_feed_reliability, which likely provides current reliability. The phrase 'history' in the tool name is reinforced by 'daily ... time-series.'

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?

The description clearly implies usage for historical reliability data ('Premium reliability history', 'daily ... time-series'). It also provides a cross-reference for getting current feed ids: 'Use the free GET /api/feed-reliability for current feed ids.' However, it doesn't explicitly contrast with the sibling tf_premium_feed_reliability or state when not to use this tool.

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