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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds real value by disclosing result shape — ids suitable for fetch, a 'first-named page' match, and an explicit none-result when no page covers the query. It does not discuss result count limits or ranking beyond 'names first', which the output schema presumably covers.

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?

Purpose is front-loaded and every clause is informational, but the long enumeration of indexed content types is dense and reads as a run-on. The domain list earns its place for keyword choice; it could have been tightened without losing meaning.

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 one-parameter read tool with an output schema and full annotation coverage, the description covers scope, return semantics, and the fallback path to sibling pricing tools. Remaining gaps (result limits, ranking order) are plausibly handled by the output schema, so nothing critical 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?

The schema labels the single parameter only as 'Keywords.' The description compensates with concrete example queries ('H100', 'Claude Opus', 'CoreWeave', 'benchmark contract') that demonstrate acceptable input granularity across entity types. That is meaningful guidance beyond the schema, though it stops short of stating matching rules such as partial words or case sensitivity.

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 ('Search Compute Screener's pages by keyword') and then enumerates exactly what content is indexed — GPUs, AI companies, models, providers, methodology, futures, electricity prices, coding tools, data center sites — with concrete example queries. This is clearly distinguishable from the sibling 'fetch', which retrieves a page by id rather than locating one.

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 implies the search-then-fetch workflow ('Returns ids for fetch') and explicitly routes the agent elsewhere when no page exists, naming get_gpu_market_prices and get_model_prices as the fallback. It does not state the inverse exclusion (if you already have an id, skip search), but the retrieval chain is clear enough for correct tool selection.

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