exa

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description only needs to add context. It contributes the output shape (clean text plus metadata) and batching behavior, but says nothing about truncation at maxCharacters or rate limits.

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?

Front-loads the core action, then uses tight 'Best for' and 'Returns' labels. Every sentence earns its place with no redundancy.

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?

No output schema exists, so the description appropriately covers the return value (clean text and metadata). It is complete for the core fetch operation, though edge behaviors like truncation are left implicit.

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%, so both parameters are already documented in the schema. The description's 'Batch multiple URLs in one call' merely restates the urls parameter and adds no syntax or format detail beyond it.

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+resource ('Read a webpage's full content as clean markdown') and distinguishes itself from its sibling by naming web_search_exa and its relationship to it. An agent can tell exactly what this tool does versus search.

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 states when to use it ('after web_search_exa when highlights are insufficient or to read any URL'), naming both the triggering alternative and the general case. The 'Best for' line reinforces the intended context.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds the return shape ('clean text content from top search results') and category-scoping behavior, which is useful but modest; there is no mention of rate limits, result freshness, or ranking behavior.

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?

Front-loaded with what the tool does, then scannable Best-for / Returns / Tips sections with no filler. The query-tip example slightly duplicates the schema wording, but the structure is clean and appropriately short.

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 no output schema, the description supplies the missing return information ('clean text content from top search results'), and annotations cover the safety profile. The category:people/company guidance is a genuinely useful extra, though result count and pagination behavior are only implied by the schema's numResults default.

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%, so the schema already documents query (semantically rich description, category: syntax) and objective (ranking/exclusion goals). The description's 'Query tips' largely restate what the schema says, so it adds little meaning beyond the structured fields – baseline 3 applies.

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+resource ('Search the web') and scopes it with a 'Best for' list covering current information, news, facts, people, and companies. The closing line naming web_fetch_exa as a follow-up partially differentiates it from the sibling, though it doesn't state outright that fetching content from a known URL is web_fetch_exa's job, not this tool's.

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?

Gives clear context for when to use it ('Finding current information, news, facts, people, companies') and explicitly routes follow-up work to web_fetch_exa when highlights are insufficient. It stops short of stating exclusions (e.g., when not to use search vs. a direct fetch), so it is clear context without full when/when-not coverage.

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