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

With no annotations, the description carries the full burden. It discloses that the archive 'can only accumulate forward — it cannot be reconstructed after the fact,' which is a critical behavioral constraint. It also notes that providers overwrite pages and drop models quietly, explaining why the endpoint exists, and mentions that price points land in a shared time series. Missing details like auth requirements or rate limits, but the most important behaviors are covered.

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 front-loaded with the core purpose, then provides context and use cases, and ends with a critical limitation. Every sentence adds value: the problem statement, the three questions answered, the pointer to series/history, and the append-only note. It is concise for the conceptual richness it conveys.

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 the 'why' and 'what' thoroughly, including specific use cases and the historical context. However, it stops short of mapping the three use cases to specific `view` values or parameter combinations (e.g., which view answers the cost question), and it does not describe output structure. The rich schema descriptions partially compensate, so the tool is usable but leaves some interpretation to the agent.

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 high (80%), so the baseline is 3. The description itself does not elaborate on any specific parameters, leaving semantics to the schema. While the `view` parameter is implicitly referenced via 'catalog' and 'events' in the schema descriptions, the tool description adds no parameter-level detail beyond the schema.

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: 'Dated archive of LLM prices, context windows, announced retirement dates and quiet delistings across 400+ models and 50+ providers.' This identifies both the resource (LLM pricing/lifecycle data) and the action (archiving). It also differentiates from sibling validation tools by focusing on model data rather than universal identifiers or country-specific facts.

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 explicitly lists three use cases: contract/budget cost lookups, dependency audits for silently removed models, and migration planning for announced/moved retirement dates. It also directs users to the `series/history` endpoint for full time-series queries, clearly delineating when to use which tool. This is exemplary usage guidance.

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