searchSearch services, case studies and articles by keyword. Returns ranked matches with a snippet and the slug to fetch next.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results | |
| query | Yes | Search terms, for example HIPAA or Apollo Federation |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the operation is read-only and idempotent. The description goes beyond that by revealing that results are ranked, include snippets, and expose a slug to fetch the full item, which is valuable behavioral context for an agent choosing how to follow up.
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 sentence covers both the action and the return shape with no filler. The core scope ('Search services, case studies and articles by keyword') is front-loaded and every clause earns its 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?
For a read-only, two-parameter search tool, the description is complete: it states what is searched, what is returned (ranked matches, snippet, slug), and implies how to fetch the full item via the slug. The lack of an output schema is sufficiently compensated by the description's return details.
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 query and limit are already documented. The description only reinforces that query is a keyword and does not add new meaning to either parameter, so the baseline of 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 uses the specific verb 'search' and names the exact resource scope: services, case studies, and articles. This clearly differentiates it from the get_* and list_* siblings, which fetch or enumerate specific content types rather than performing keyword search.
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: search when you need keyword-based ranked matches across those content types. However, it does not explicitly explain when to prefer list_* or get_* tools instead, leaving the routing decision mostly to inference from sibling names.
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 maps to a distinct resource or action: individual articles, case studies, services, profile, ventures, contact info, and search are clearly separated. The only mild overlap is contact details appearing in both get_profile and get_contact_and_booking, but their purposes remain distinct.
Tool names follow a consistent get_<singular> / list_<plural> convention, with search as a single clear outlier. The pattern makes it easy to predict that list_* returns collections and get_* returns one item.
Ten tools is well-scoped for a personal website and consulting content server. Each tool covers a meaningful retrieval need without redundancy or bloat.
The server provides complete read-side coverage for the apparent domain: listing and retrieving articles, case studies, and services, plus profile, ventures, contact, and cross-content search. No create/update/delete operations are needed for a public content site, so there are no meaningful gaps.