set_learned_profileRead or rewrite the free-text profile the briefing uses to know who this person is — their work, projects, recurring interests, what they already know. Appending is usually better than replacing: pass mode "append" to add a line.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Default append | |
| text | Yes | The profile text, or the line to add |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare destructiveHint=true and readOnlyHint=false, and the description aligns by saying 'rewrite' and 'append'. It adds valuable context that replacing destroys existing profile content while appending preserves it, which goes beyond the annotation's bare destructive flag. No contradiction found.
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, front-loaded with the core purpose, followed by actionable guidance. No redundant filler; every clause earns its place. The structure is clean 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?
The description covers the tool's purpose, profile content, and mode semantics, which is sufficient for a simple setter with no output schema. However, the odd 'read or rewrite' phrasing could confuse an agent about whether a read-only retrieval is possible, creating a minor completeness gap.
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% with descriptions for both parameters. The description enhances this by explaining how 'text' behaves depending on mode ('add a line' for append vs. implied full replacement) and reinforces the default append behavior, adding meaning beyond the schema's enum and field descriptions.
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 identifies the resource (the learned profile) and actions ('read or rewrite'), but the dual verb 'read or rewrite' is ambiguous; the tool name and schema indicate it is primarily a write operation. It distinguishes from siblings by clarifying the profile's role in briefings, but the ambiguity mildly weakens purpose clarity.
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 provides clear guidance on mode selection ('Appending is usually better than replacing: pass mode "append" to add a line'), but does not explicitly state when to use this tool versus alternatives like correct_briefing or tune_topic. Usage context is implied by describing the profile's purpose, but no exclusions are given.
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.