searchSearch the Muralists directory of muralists and street artists by free text (name, city, style). Returns matching artists with their profile URLs. Use fetch with a returned id to read the full profile.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Free-text search query, e.g. 'lettering artist Utrecht'. |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only, so no side-effect disclosures are needed. The description adds behavioral value by clarifying that results are limited to matching artists and profile URLs and that full profile content requires a separate fetch call – a useful boundary beyond the annotations. No contradictions.
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: the first front-loads the action and scope, the second adds the return format and next step. Every word earns its place; no redundancy.
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 one required parameter, a read-only annotation, and an existing output schema, the description supplies the essential usage flow and return shape. The only remaining gap is the relationship to the search_muralists sibling, which prevents a 5.
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 only parameter (query) is already fully described in the schema (100% coverage), giving a baseline of 3. The tool description enriches this by specifying what the free-text query can target – name, city, style – which is not present in the schema. Thus it earns a 4.
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 opens with a clear verb and resource – 'Search the Muralists directory' – and enumerates searchable facets (name, city, style). It distinguishes itself from fetch/get_muralist_profile by noting that only profile URLs are returned and that fetch is needed for full profiles. However, it does not differentiate from the sibling search_muralists, leaving ambiguity between the two search tools.
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 a concrete workflow: run a free-text search, receive profile URLs, then 'Use fetch with a returned id to read the full profile.' This is clear context for when this tool fits. It does not state explicit exclusions or when to prefer search_muralists, 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.
Add one secure layer between your agents and this server.
The tools form two overlapping pairs: search/search_muralists and fetch/get_muralist_profile. The descriptions add some distinction, but an agent could easily select the wrong tool without careful reading.
Names mix generic verbs like fetch and search with more specific verb_noun forms like get_muralist_profile and search_muralists. The pattern is readable but not consistent across the set.
Four tools is a reasonable number for a directory-oriented server. However, two of the tools are largely redundant, so the effective surface is smaller than the count suggests.
The server covers the core directory workflow: searching for muralists and retrieving detailed profile information. It lacks broader browsing or direct contact/quote actions, but these are minor gaps for a read-only directory.