Agents in the Wild

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. With no output schema, the description does add value by listing the fields the result contains, but it says nothing about cost of a full-dataset scan, caching, or whether the statistics are live or precomputed.

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?

A single front-loaded sentence lists the returned aggregates with no filler or repetition. It is efficient, though the bare field list leaves the return content slightly telegraphic compared to a fuller statement of purpose.

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 zero-parameter, read-only statistics tool with no output schema, enumerating the aggregate categories is the essential information an agent needs. Missing only framing about when to prefer it over the record-level siblings.

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 tool takes zero parameters, so there is nothing for the description to explain; baseline 4 applies. The description correctly implies the scope is the entire dataset with no filtering options, matching the empty 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?

Opens with a specific verb+resource ('Statistics over all entries') and enumerates the aggregates returned (evidence mix, self-reported share, categories, industries, top tools, years), so the agent knows exactly what data comes back. It does not explicitly contrast itself with get_use_case or search_use_cases, so sibling differentiation is only implicit.

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?

'over all entries' hints that this is unfiltered aggregate data rather than a record lookup, which weakly distinguishes it from the sibling search/get tools. However, there is no explicit statement of when to choose this over search_use_cases, no prerequisites, and no mention that no filtering parameters are accepted.

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=true and openWorldHint=false, so the safety profile is covered. The description adds value by disclosing the shape of the payload, including qualitative fields (evidence label, caveats) that signal data reliability, but says nothing about missing-slug behavior or whether entries can be absent.

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?

One compact clause with the key framing ('Full entry by slug') front-loaded, followed by a field list — no filler. The fragmentary grammar is terse but not ambiguous in this context.

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 present, the description usefully enumerates the returned fields, which is the main thing an agent needs to know. For a one-parameter read tool with clear annotations, nothing essential is missing beyond error behavior for unknown slugs.

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% and the single slug parameter is fully documented with an example, so the baseline is 3. The description contributes no additional semantics about slug format or normalization beyond what the schema already states.

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 'Full entry by slug' plus the enumerated fields (summary, outcome, metrics, evidence label, caveats, source links) makes it clear this retrieves a single full record rather than a list, which implicitly distinguishes it from the sibling search_use_cases. It stops short of an explicit verb like 'retrieve', relying on the title for that framing.

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 direct statement of when to choose this over search_use_cases; the workflow is only implied via the schema note that the slug comes from search_use_cases. An agent can infer the search-then-fetch pattern, but the description itself offers no explicit trigger condition or exclusion.

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 read-only and closed-world, so the description's value lies in disclosing data-quality behavior: results carry a reported outcome plus an evidence label identifying the claimant, and quoting requires verification via get_use_case. That is meaningful context an agent could not infer from the annotations.

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?

Two short sentences with no filler: the first states what is returned, the second states the required next step. The critical provenance caveat is placed last, but everything earns its place.

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?

Six optional parameters and no output schema, yet the description conveys the shape of a result (outcome plus evidence label) and the verification workflow. Gaps remain around matching behavior, result ordering, and the effect of limit, but the essentials for correct invocation are present.

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 only 50% — category, industry, and limit have no schema descriptions — and the description adds no information about any parameter, not even how query matches or how evidence filtering interacts with the result labels. The description does not compensate for the coverage gap.

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 real, sourced AI agent deployments at named organizations') and distinguishes itself from the sibling get_use_case by describing results as search hits and routing detail lookup to get_use_case.

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 an explicit follow-up rule ('Call get_use_case for sources and caveats before quoting a result'), which is real workflow guidance. It does not state when to prefer this search over get_dataset_stats or what to do when a query returns nothing, so it stops short of 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.