Excellent Reference (free)

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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses result cardinality and ordering ('up to 3 passages, best match first') and that each result carries the in-app page it starts on. It also states the auth and data-scope profile ('no account needed; reads no restaurant group's data'), which is meaningful context the annotations don't convey.

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 core definition is front-loaded and the second sentence covers returns and access profile efficiently. The long parenthetical domain list is dense but each item is informative for match prediction, so little is wasted.

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 correctly takes on the burden of explaining return shape (count, ordering, page attribution) and privacy/auth posture. The only remaining gap is sibling disambiguation against search_excellent_pages.

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 coverage is 100% with a single well-described query parameter including examples, so the schema does the heavy lifting. The description implies natural-language lookup but adds no syntax, formatting, or length guidance beyond what the schema already provides; baseline 3.

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 states a specific resource (Excellent's own help text / assistant source passages) and enumerates the concrete task domains it covers, so an agent knows exactly what kind of content comes back. It does not, however, differentiate itself from the sibling search_excellent_pages, which sounds like a near-neighbor.

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?

Usage is implied by the framing ('how to do a task in Excellent') and the query field example, and the 'no account needed' note removes a prerequisite concern. But there is no explicit when-to-use vs when-not, and the sibling search_excellent_pages is never mentioned as an alternative.

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 readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description still adds useful behavior beyond them: a hard result cap of 5, the shape of returned items (URL plus the page's own summary text), and the no-auth precondition.

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 in the first clause, return shape follows, and the auth note closes. No filler sentences and nothing repeated from the schema.

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 correctly fills that gap by stating the result count ceiling and returned fields. For a two-parameter read-only search tool, an agent has everything needed to call it correctly.

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 coverage is 100%, so the baseline is 3; the description earns an extra point by explaining what 'comparison' pages actually contain (wins per platform, last-reviewed date), which enriches the kind enum beyond its terse schema note 'Optional: only one kind of page.'

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?

Opens with a specific verb and resource ('Search Excellent's published pages') and enumerates exactly what is searchable (feature, comparison, blog). An agent can tell what it retrieves, though it never explicitly contrasts itself with the sibling excellent_help tool.

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 account needed' and the enumeration of page kinds give clear context for when this tool applies (looking up product features, competitor comparisons, blog content). It stops short of stating when NOT to use it or naming excellent_help as the alternative for general help.

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