list_citiesList the 24 cities Dim Hour covers, with the city key to pass to the other tools.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| cities | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is established. The description adds the concrete detail that the result is a fixed set of exactly 24 cities, reinforcing the closed-world annotation, but adds nothing about edge cases or error behavior. This is modest value beyond the annotations, consistent with a 3.
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 18-word sentence places the verb and resource first, then the key-purpose detail. Every word earns its place; there is no repetition of the title or annotations.
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 enumeration tool, the description plus annotations and output schema are fully sufficient. It states the count, the scope (Dim Hour), and the purpose of the returned key, while safety is covered by annotations and return shape by the output schema.
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 has zero parameters, so the baseline of 4 applies; the description correctly implies no inputs are needed. Schema coverage is 100% vacuously, and the description does not mislead about any inputs. There is nothing further to document.
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'), a concrete resource ('the 24 cities Dim Hour covers'), and a precise scope (a fixed set of 24). It also states what the output is for ('city key to pass to the other tools'), leaving no ambiguity. Sibling tools are all venue/search operations, so this enumeration tool is clearly distinguishable by domain.
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 phrase 'with the city key to pass to the other tools' gives clear contextual guidance: this is a prerequisite lookup for downstream city-keyed calls. It does not have explicit when-not conditions or named alternatives, but given that every sibling tool operates on venues or searches, the routing is self-evident.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
fetch and get_venue both retrieve essentially the same full venue record, differing only by an extra long-form story field. Similarly, search and search_venues both search the same catalog and return ranked venue results, making it unclear which one an agent should call and creating real misselection risk.
The list_* tools are consistent and readable, and most tools use snake_case verb_noun naming. However, fetch and search are bare verbs, and fetch vs get_venue introduces two different verbs for the same operation, so the overall pattern is mixed but still understandable.
Seven tools is a reasonable size for a venue guide server, but the count is slightly padded because fetch duplicates get_venue and search duplicates search_venues. The effective surface is closer to five distinct tools, so the count is slightly over what is needed.
The read-only domain is well covered: city discovery, search, curated editorial lists, new venue updates, and full venue details are all present, and search naturally leads into detail retrieval. Minor gaps exist, such as no dedicated non-search way to browse all venues in a city, but the core workflows have no dead ends.