Things To Do API

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

With no annotations, the description carries the full behavioral burden. It does disclose the return contents ('all its tags, venue, links and times'), which is genuine value, but says nothing about read-only semantics, auth requirements, or what happens with an unknown/invalid id.

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 tight sentence, front-loaded with the core purpose and well within budget. Every clause 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?

For a simple one-parameter read tool with no annotations or output schema, the description covers both the source of the input id and the shape of the returned record. Only minor gaps remain around error behavior and edge handling.

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?

One required parameter at 0% schema coverage, so the description must compensate and only partially does: it establishes that 'id' identifies a single event and comes from search_events. It adds no format or validity constraints for the id itself.

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 ('Everything known about one event by its id') and enumerates the payload (tags, venue, links, times). The parenthetical '(from search_events)' implicitly contrasts it with the sibling that supplies ids, though it never names list_coverage or explicitly frames itself as the detail counterpart to 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?

The '(from search_events)' note gives an implied workflow: obtain an id from search_events, then call this. That is useful context, but there is no explicit when-to-use/when-not statement and no mention of how it relates to list_coverage.

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?

No annotations are provided, so the description carries the burden. It implies a read-only reference listing and states what the payload covers, but never says so explicitly (no read-only, auth, or freshness claims). For a zero-argument lookup the risk is low, so this is adequate rather than rich.

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 zero filler, and the payload contents are front-loaded before the usage trigger. Every clause 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?

There is no output schema, so the description must hint at the return shape; it does so by naming the three things returned (metros, cities, categories). It could say more about format or freshness, but for a no-arg reference tool this is close to complete.

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, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies the tool is unfiltered and returns the full coverage set.

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 names the specific resource it returns (metros, cities, and categories of coverage), which is more than a restatement of the name. It does not explicitly distinguish itself from get_event or search_events, but the resource is clearly a reference/coverage listing rather than event retrieval.

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?

"Call it when unsure whether a city is covered" gives an explicit triggering condition, which is unusually concrete for a lookup tool. It stops short of stating when-not to use it or naming an alternative sibling, so it misses the top band.

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, the description carries the full burden and does substantial work: it discloses return contents (local-timezone start times, venue, summary, tags, ticket/source links, match reasons), the geographic coverage limit and its failure mode (out-of-area returns not covered, no events), and that `from` overrides query time. It omits any auth, rate-limit, or latency behavior, keeping it short of a 5.

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 the verb and resource, and every subsequent sentence adds invocation or return-value information. The lengthy category enumeration and audience phrasing examples make it denser than strictly necessary, but nothing is filler.

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 9-parameter tool with a nested `near` object, no output schema, and no annotations, the description covers the essentials: what comes back, coverage boundaries, and pagination. Remaining gaps (sort semantics, category enum meaning, limit bounds) are minor because the schema already documents them.

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 already 89%, so the baseline is 3, but the description adds real meaning: `query` accepts natural language embedding time/place/audience, `from`/`to` override time in the query, and `offset` should be fed the returned next_offset. It does not clarify `sort`, `categories` enum values, or `limit` bounds beyond the 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?

States a specific verb and resource ('Find events happening in a city') and then enumerates the concrete domains covered (concerts, club nights, comedy, markets, festivals, classes), so an agent knows exactly what this retrieves. The coverage statement also implicitly separates it from the sibling list_coverage/get_event without needing to name them.

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 guidance on how to invoke: pass plain words in `query`, include who it is for in the same words, and use from/to/place/near 'when you already know them exactly'. Also explains the pagination path (re-call with next_offset). It stops short of naming alternative tools or explicit when-not-to-use conditions.

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