Search the TESSA Professional Services Directory.
industry: segment slug ('marketing' | 'compliance')
or free-text keyword
region: city or state name (case-insensitive contains)
capability: keyword to match against firm descriptions and service names
limit: max results
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| region | No | ||
| industry | No | ||
| capability | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only says 'Search' and documents parameters; it does not disclose what the search returns, whether it's read-only, how filters combine, or potential limitations. For a search tool, this lack of behavioral context (e.g., pagination, result format) is a significant gap.
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?
The description is concise and well-structured: a single opening sentence followed by a clearly formatted parameter list. Every line adds value, and the code-block layout makes the parameter documentation easy to scan. There is no fluff or 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?
The description covers parameters effectively but is incomplete in other respects. It lacks any mention of return values (no output schema), how the filters interact, or search behavior beyond parameter matching. For a multi-filter search tool with no annotations, this is a moderate gap, but the parameter semantics are solid.
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?
With 0% schema description coverage, the description fully compensates by documenting each parameter: industry (segment slug or free-text), region (case-insensitive contains), capability (keyword matching), and limit (max results). This adds substantial meaning beyond the raw schema, clarifying expected input formats and matching behavior.
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 clearly states the tool's function: 'Search the TESSA Professional Services Directory.' The verb+resource is specific and the tool name 'find_professional_services_firm' reinforces that it locates firms. However, it doesn't explicitly distinguish this from sibling tools like get_firm_profile or get_services, though those serve different purposes, so it's clear but not fully differentiated.
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 description implies usage: use this tool to search the directory for professional services firms. It does not provide explicit when-to-use vs alternatives, nor exclusions, but the name and context suggest it's the appropriate tool for directory searches. No guidance is given on when other tools like request_introduction or get_case_studies would be more suitable.
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.
Each tool has a clear, distinct purpose. The get_* tools retrieve different data types (services, firm profiles, case studies, audit offerings), the request_* tools target different actions (introduction, quote, strategy session), and assess_ai_readiness and claim_listing are unique. No two tools appear to do the same thing.
Tool names are all snake_case and follow a verb_noun structure, but the verbs vary (assess, claim, find, get, request) rather than using a single consistent pattern. The get_ and request_ subgroups are internally consistent, so the naming is readable and predictable despite the variety.
With 10 tools, the server is well-scoped. Each tool serves a clear function in the marketing/directory domain: discovery (find, get), engagement (request, claim), and assessment (assess, get_wcag_audit). The count is neither sparse nor overwhelming.
The surface covers the core workflows: searching the directory, retrieving firm details and services, requesting intros/quotes/sessions, claiming listings, and checking AI readiness. Minor gaps exist (e.g., no tool to update a listing or access the compliance registry directly), but these are not likely to cause agent failures.