Manchester Tonight

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered; the description adds return-content context (times, address, sources, last-checked timestamp) and the important caveat 'address if known', which signals that fields may be missing. That is real behavioral value beyond 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?

A single front-loaded sentence with no preamble or filler. The trailing return-value list is slightly run-on but each item carries information, so it is efficient overall.

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 carries the burden of describing returns and does so adequately (times, address, sources, last checked), and 'every regular night' implies a complete rather than paginated result. Minor gaps remain around result ordering or error behavior when a venue is unknown.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents the venue argument with examples. The description adds only the geographic constraint ('Manchester venue') and no syntax or matching rules, so 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 (Get) and resource (every regular night at one Manchester venue), with enough scoping detail that an agent can distinguish it from search_listings, seasonal_events, and whats_on without opening the schema. It does not name a sibling explicitly, so it stops short of the top score.

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 only implied: the venue-scoped 'regular night' framing suggests it is for looking up a known venue's recurring schedule rather than discovering events. There is no explicit when-to-use or when-not-to-use guidance and no alternative named.

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, idempotentHint and openWorldHint=false, so the safety profile is covered, and the description goes beyond them by disclosing what comes back ('Results include the day rule, e.g. Every Tuesday, 1st Thursday of the month'), which is genuinely new information with no output schema to carry it. It still says nothing about match strictness (fuzzy vs exact keyword matching) or result ordering.

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?

Three sentences: capability first, then concrete example questions, then the notable return field. Nothing is repeated and nothing is padding.

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 accepts the burden of hinting at the return shape and does so via the day-rule sentence, and its usage examples cover the main intent classes. Minor gaps remain around result ordering and matching behavior, but an agent has enough to call this 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 description coverage is 100%, so every parameter including day, area, type, limit and query is already documented in the schema with examples and enumerations. The description's recital of 'keyword, area, type and day of the week' adds no format or matching semantics beyond that, so the 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 and resource ('Search all regular nights out in Manchester') plus the filter dimensions, which is unambiguous. It implicitly separates itself from seasonal_events and whats_on via the word 'regular' (recurring nights vs one-off events), but never names those siblings explicitly, so an agent must infer the boundary.

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?

Concrete example queries ('free comedy in Manchester', 'which pubs in Stockport have a quiz', 'open mics on Mondays') give the agent clear situational context for when to reach for this tool. It stops short of saying when NOT to use it or pointing to whats_on / seasonal_events for one-off events, so the routing guidance is implied rather than explicit.

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 readOnlyHint, openWorldHint=false, and idempotentHint already declaring the safety profile, the description adds useful return-format context: 'dates, times, prices and a ticket link.' It does not disclose rate limits, authentication needs, or pagination, so it misses some operational detail.

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?

Three front-loaded sentences: purpose and scope first, example queries second, return fields last. Every sentence earns its place and there is no 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 simple read-only listing tool with one optional parameter and no output schema, the description covers scope, usage examples, and return contents. Nothing essential for correct invocation appears to be missing.

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%, and the single optional 'season' parameter is fully documented in the schema. The description mentions seasonal examples but adds no format, default, or allowed-value guidance beyond the schema, so the baseline of 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?

The description gives a specific verb and resource: 'List upcoming dated seasonal events in Manchester,' with concrete examples of event types. It does not explicitly differentiate itself from siblings like whats_on or search_listings, so it falls short of full sibling contrast.

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?

It provides clear usage context via example queries such as 'Halloween in Manchester' and 'Christmas markets dates.' However, it does not state when to prefer this tool over siblings or when not to use it, leaving alternatives to inference.

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, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the shape of each result (time, venue, area, notes, and a link to cite), which matters because no output schema exists. It does not discuss empty-result behavior, rate limits, or result ordering.

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?

Three sentences, front-loaded with the core purpose, then usage examples, then the return shape. The category enumeration is long but each term is a genuine matching surface for user queries, so no sentence 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 usefully compensates by naming the returned fields, and all four parameters are fully documented in the schema. The main remaining gap is operational context such as pagination/limit interaction with the default of 30 or what a no-results response looks like, but nothing essential to correct invocation is missing.

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%, and the schema itself carries rich semantics for every parameter, including the UK-time / pre-4am "tonight" rule and the accepted area and type vocabularies. The description adds no parameter-level detail beyond what the schema already states, aside from the example queries that implicitly exercise area/type. Baseline 3 is appropriate when the schema does the heavy lifting.

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 a specific verb ("List") and resource ("regular nights out and one-off events in Manchester, UK") and scopes it to a given date, with an explicit enumeration of categories (pub quizzes, comedy, open mics, live music, club nights, drag, happy hours). It is unambiguous about what the tool returns. However, it never names or contrasts with its siblings (get_venue, search_listings, seasonal_events), so sibling differentiation is left to inference.

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?

Three natural-language example queries ("what's on tonight in Manchester", "comedy in the Northern Quarter on Saturday", "quiz in Didsbury tomorrow") give a clear picture of the triggering intent and map directly onto the area/type/date parameters. There is no explicit when-not-to-use guidance and no mention of the alternative tools, so it stops short of a 5.

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