work_by_topicUse this when someone asks what Cameron Wilson has published on a particular topic. Match declared or derived topics, titles, and text.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| topic | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | ||
| items | Yes | ||
| title | No | ||
| description | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the operation as read-only and idempotent. The description adds useful behavioral detail: it matches 'declared or derived topics, titles, and text', indicating fuzzy or broad matching rather than exact match only.
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 two sentences, front-loaded with the usage trigger, and each sentence adds value. No redundant or filler language.
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 tool has a small parameter set, an output schema, and clear annotations. The description covers purpose and matching behavior sufficiently. It could be more explicit about how it differs from 'search' or 'search_journalism', but the topic-specific focus makes it adequate.
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 description coverage is 0%, so the description must compensate. It clarifies that 'topic' is matched against topics, titles, and text, and may include derived topics. However, it does not add meaning for the 'limit' parameter, which remains self-explanatory only through 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?
The description clearly states the tool's purpose: to retrieve what Cameron Wilson has published on a particular topic. The verb 'use this when' plus the specific subject (Cameron Wilson) and matching logic (topics, titles, text) distinguishes it from sibling tools like latest_work or featured_work.
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 explicitly says to use this when someone asks about Cameron Wilson's publications on a particular topic. It does not list exclusions or alternatives, but the context is clear enough for an agent to select this tool over siblings.
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.
Multiple tools overlap in purpose: search vs. search_journalism both search but differ in advanced filters; fetch vs. get_item both retrieve by ID but with different output types; featured_work vs. recommended_reading both return curated lists. The descriptions help somewhat but boundaries remain unclear for an agent.
Tool names mix styles: bare verbs (fetch, search), verb_noun (get_item, search_journalism), and descriptive phrases (featured_work, latest_work, recommended_reading, work_by_topic). No consistent pattern across all names.
With 8 tools covering search, retrieval, and curated lists, the count is well-scoped for a specialized journalism archive. Each tool serves a distinct niche, and the number is within the ideal 3-15 range.
The surface covers the major workflows: general search, advanced search, item retrieval, and curated/featured lists. Minor gaps like bulk listing or topic enumeration without search exist but are addressable via search_journalism.