nyc-tennis-courts

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

With no annotations, the description carries the transparency burden. It discloses a read-only search behavior, the filter semantics, and the return value (venues with page URLs). The note about indoorOnly excluding unresearched venues rather than assuming they are outdoor adds valuable behavioral detail beyond the schema.

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 sentences deliver the full purpose, filter capabilities, and return behavior with no filler. The main action is front-loaded, and the conservative indoorOnly behavior 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?

The description explains the key filters and states that each returned venue includes its page URL, which is enough for an agent to invoke the tool and continue with get_court. It does not enumerate all return fields, but the absence of an output schema is mitigated by the explicit URL mention.

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 input schema already covers all 5 parameters with 100% description coverage, so the baseline of 3 applies. The description lists some filter categories, but it does not add meaningful semantic detail beyond what the schema already provides for each parameter.

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 clearly states a specific verb ('Search') and resource ('the directory of places to play tennis in New York City'), and lists concrete filter dimensions. It does not explicitly distinguish itself from siblings like get_court, but the directory-search framing is distinct enough to be unambiguous.

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 tool is for finding a list of tennis venues while providing no explicit guidance about when to prefer it over get_court or how_to_play_tennis_in_nyc. It gives clear context for its own use but no exclusions or alternative routing.

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?

With no annotations provided, the description carries the full behavioral burden. It discloses the comprehensive data returned (courts, surfaces, floodlights, accessibility, etc.) and adds provenance ('source each fact was read from'), which is valuable context. It implies a read operation without side effects, though it doesn't explicitly state that it is non-destructive, but the description is sufficiently transparent about its scope.

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 two sentences, front-loaded with the core purpose ('Everything the directory holds about one venue') and then lists specific details. Every sentence earns its place—no fluff, no repetition. It's both concise and informative.

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 tool with a single parameter, no output schema, and no annotations, the description is fully self-contained: it explains what the input is, where it comes from, and what the output includes. The enumerated data fields effectively substitute for an output schema, and the description is complete given the tool's simplicity.

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 already provides 100% coverage with a clear description ('Venue slug, e.g. central-park. From find_courts.'). The description restates the origin ('Takes the slug returned by find_courts') but adds no new semantic meaning beyond reinforcing the source. According to the baseline for high schema coverage, a score of 3 is appropriate.

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 clearly states 'Everything the directory holds about one venue' and enumerates specific data fields (courts, surfaces, floodlights, etc.). It distinguishes from sibling find_courts, which presumably returns a list of venues, by focusing on full detail for a single venue.

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 instructs that it 'Takes the slug returned by find_courts', establishing a clear usage pattern. It doesn't explicitly state when not to use it or name alternatives, but the dependency on find_courts makes the workflow explicit, so the guidance is strong though not exhaustive.

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?

With no annotations provided, the description fully carries the burden of disclosing behavior. It explains the tool corrects a common misconception and warns against relying on general knowledge, setting clear expectations for the kind of information it returns.

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 three sentences long, each with a distinct purpose: instructing the user, detailing the return value, and explaining the necessity. It is front-loaded with the most important imperative ('Start here') and contains no unnecessary verbiage.

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 parameterless tool with no output schema, the description fully sets expectations about what the tool does and why it is needed. It covers the return content and the reasoning behind the tool's existence, making it complete for an agent to decide to invoke it.

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 no parameters (schema is an empty object), so per the rubric the baseline is 4. The description cannot add parameter-level detail, but it compensates by describing the conceptual scope of the tool.

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 clearly states its purpose: it is a 'Start here' guide for answering any question about playing tennis in NYC. It specifies exactly what it returns—'the real split between courts you walk on to, courts you reserve, and private clubs, plus what a permit costs'—which distinguishes it from sibling tools like find_courts and get_court.

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 provides explicit guidance on when to use the tool ('Start here before answering any question about playing tennis in New York City'), establishing it as the entry point. It does not name sibling tools or provide explicit when-not scenarios, but the directive is strong enough to guide an agent's decision.

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