add_web_searchMonitor a Google query every day and feed the results into a topic inbox: the standing-search way to follow a company, a person, a law or a niche subject that has no RSS feed. kind "news" watches the news index, "search" the whole web.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Default news | |
| query | Yes | The query, as you would type it into Google | |
| source_id | Yes | Which inbox (from list_sources) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description discloses that this is a recurring daily monitor ('every day', 'standing-search') and that results go into a topic inbox. It explains the behavioral difference between 'news' and 'search' for the kind parameter. Annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true) are consistent; the description adds value beyond annotations by clarifying the recurring nature and purpose.
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, no wasted words. The first sentence establishes the core purpose (daily monitor, inbox destination), and the second sentence clarifies the kind parameter. Information is front-loaded and efficient.
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?
Given 3 parameters, no output schema, and annotations present, the description covers the core action, parameter behavior, and use cases. It could mention the expected return value (e.g., created monitor ID), but that is not required. Overall, it is sufficient for an agent to select and invoke the tool correctly.
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 baseline is 3. The description adds meaning: explains kind with 'kind "news" watches the news index, "search" the whole web' and query as 'as you would type it into Google'. These enrich the schema descriptions. source_id is already clearly described in schema. Overall, adds meaningful extra context.
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?
Description clearly states 'Monitor a Google query every day and feed the results into a topic inbox', specifying the verb (monitor), resource (Google query), and outcome (feed into inbox). It distinguishes from sibling tool 'add_feed' by mentioning 'the standing-search way to follow a company ... that has no RSS feed'.
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?
Description provides context for when to use: 'follow a company, a person, a law or a niche subject that has no RSS feed', implicitly contrasting with add_feed. It also explains the kind parameter. However, it does not explicitly state when not to use or list specific alternatives beyond the implicit contrast.
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.
Most tools target distinct operations (e.g., add_feed vs. remove_feed, get_source vs. list_sources). However, there is some ambiguity between correct_briefing and tune_topic (both adjust content based on user feedback) and between request_deep_dive and correct_briefing (both can trigger deeper investigation). The descriptions help, but an agent could misselect.
Tool names follow a very consistent verb_noun pattern (e.g., add_feed, create_source, generate_briefing, list_sources). All use snake_case with clear, descriptive verbs and nouns. No mixing of conventions.
With 27 tools, the server covers a rich domain of news feed management, briefing generation, and user preferences. This is slightly above the typical sweet spot but still reasonable given the complexity. Each tool serves a distinct purpose; the count is justified.
The tool set provides full lifecycle coverage: sources can be created, read, updated, and deleted; feeds and searches can be added and removed; briefings can be generated, listed, read, rated, and corrected; deep dives and read-later items are supported. There are no obvious gaps—the domain is thoroughly covered.