Gilbert First

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior. The description adds meaningful context beyond that: the sort order (rating then review count), the review-count floor with its default, and the ratings source with an as-of date caveat.

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 use cases, then ranking mechanics, in two tight sentences with no filler. Every clause carries information.

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?

An output schema exists, so return values need no explanation, and the ranking/source semantics are covered. The one gap is the unexplained `limit` parameter, whose behavior an agent must guess.

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 only 33%, with only `topic` described. The description compensates by illustrating topic values and stating the min_reviews default of 50 (not in schema), but `limit` is never mentioned and its role is left unexplained.

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 (ranks) and resource (places in the Gilbert First directory) plus the exact ranking criteria (Google rating, then review count). This is clearly distinct from siblings like gilbert_business_lookup or gilbert_events without needing to open any schema.

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 ("best brunch in Gilbert", "top coffee shops") make the intended invocation context obvious. It does not explicitly name which sibling to use for non-ranking lookups, so routing against alternatives is left slightly implicit.

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 closed-world scope, so the safety profile is covered. The description still earns credit for disclosing the not_found return behavior and the shape of the payload, though it doesn't say what happens when the name is ambiguous or whether multiple matches collapse to one.

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 dense, front-loaded sentence that puts the use case first and then the returned fields, with zero filler. It is a long sentence, but every clause carries information an agent needs, so the compression is justified.

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 two-parameter read-only lookup with an output schema present, the description covers the use case, the returned content, and the failure mode. Nothing needed to invoke it correctly 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 coverage is 100%, so both parameters are already documented in the input schema. The description reinforces that the lookup targets a single named business but says nothing about how the optional category narrows or disambiguates results, so it adds little beyond the structured fields — 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?

A specific verb ('look up') plus a precisely scoped resource ('one named business in Gilbert, AZ'), and it enumerates what comes back: address, phone, website, rating, directory page, openings-tracker status. That single-business scope cleanly separates it from sibling list-style tools such as gilbert_best_of and gilbert_events without requiring a schema read.

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?

'Use for one named business' gives clear positive guidance on the triggering case, and the mention of the openings tracker implicitly points at how it relates to gilbert_openings. It stops short of stating when NOT to use it (e.g., for browsing categories or unnamed searches, where the siblings fit), so no explicit 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds real behavioral scope beyond the annotations: the tool is limited to *upcoming* meetings and *published* agendas, so an agent knows unpublished or historical items will not appear. It does not address rate limits, empty-result behavior, or result volume.

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, front-loaded with the usage triggers before the return contents, with no filler. The quoted query examples are dense but each maps to a distinct item type (agenda, liquor, rezoning), so they earn their 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?

With only one optional parameter, an output schema handling return values, and rich safety annotations, the description covers what an agent needs to decide and call correctly. The remaining minor gap is that it never mentions the `days` window, leaving the agent to discover the default horizon from the schema alone.

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?

There is a single optional parameter, `days`, and the schema already documents its meaning, default of 30, and the 1-90 range at 100% coverage. The description says nothing about the time window, so it adds no meaning beyond the schema. Baseline 3 applies 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 the specific resource (upcoming Town Council meetings and published agenda items) and enumerates the sub-domains returned: liquor, zoning, development items, and liquor licenses awaiting a vote. It also quotes representative user questions, which lets an agent match this tool against a query without opening the schema. It is clearly distinct from the sibling tools (best_of, business_lookup, events, openings), none of which cover council agendas.

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?

"Use for ..." plus three concrete example phrasings give a clear trigger condition for selecting this tool. There are no explicit exclusions or named alternatives (e.g. what to use for past meetings or non-council civic items), which is the only thing keeping it from a 5.

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, and closed-world, so the safety profile is fully covered. The description adds real value beyond that: it discloses the data sources, the default date window, and the shape of the returned items. It does not mention limits on result size or pagination, but the limit parameter's max of 30 hints at that.

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 with no waste; the use cases are front-loaded and the default-window rule comes last where it acts as a fallback instruction. Every clause carries information.

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 an output schema present, the description needn't spell out return values, yet it summarizes them helpfully. Annotations cover safety and the source/default behavior is stated. Minor gap: query-matching semantics and result limits are left to structured fields.

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 50%, and the description clarifies the date-range behavior (no dates => next 7 days) and implies free_only and query through its example phrasings. However it says nothing about the `when` enum values or the `limit` cap, leaving those entirely to the schema. Baseline 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 states a specific verb (returns things to do) and resource (events in Gilbert, AZ), names the two underlying sources (Town of Gilbert calendar and Eventbrite), and enumerates the returned fields. It is clearly distinct from siblings like gilbert_business_lookup or gilbert_council_watch.

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 gives concrete trigger phrasings ("this weekend", "today", "free events", specific dates) and states the default behavior when no dates are supplied (next 7 days). It does not state explicit exclusions, but the sibling tools are far enough apart in purpose that no alternative routing is needed.

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 cover read-only, idempotent, closed-world, non-destructive. The description adds real value beyond them: provenance of the records, the meaning of the status values (filed, confirmed, already open), the fields returned (area, address, council vote date, source link), and the explicit limitation "Never states an opening date."

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 highest-signal usage phrases, then scope, then the output contract and caveat. Dense but every clause carries information; the quoted phrase list is slightly repetitive but serves as retrieval bait.

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 an output schema present and annotations covering safety, the description only needs to explain intent, sourcing, and limitations — all of which it does, including the no-opening-date caveat. Coverage of the bare `limit` parameter is the only real omission.

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?

Query and status already carry schema descriptions (67% coverage), and the description largely restates them (status default, area/kind examples). The untyped `limit` gets no explanation in either place, so it neither compensates for the gap nor adds much 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 resource (new restaurants and shops in Gilbert) and names its data sources (Town of Gilbert liquor-license list, county permits). That scoping clearly separates it from siblings like gilbert_business_lookup (existing businesses) and gilbert_council_watch (votes).

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 lead-in maps concrete user phrasings ("what is opening in Gilbert", "is <name> coming to Gilbert", neighborhood names) to this tool, which gives an agent a clear trigger. It stops short of naming an alternative sibling or stating when not to use it, so it falls below a 5.

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