Walk through the temperature check interaction for a demo contact: shows the prompt and the Positive / Neutral / Concern options, and returns a canned acknowledgment. Demonstrates the loop without saving anything.
| Name | Required | Description | Default |
|---|---|---|---|
| read | No | Optional: the read to simulate. Omit to just see the prompt. | |
| contact | Yes | Contact id or name, e.g. 'Isabella Chen' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility. It discloses key behaviors: it shows a prompt and canned options, returns a fixed acknowledgment, and performs no persistence. This covers side effects and expected interaction, though it could mention what happens if 'read' is omitted.
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, densely packed with purpose, behavior, and constraints, with no fluff or repetition. Everything 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 demo tool with low complexity, the description covers the essential loop, the absent persistence, and the canned output. It lacks an explicit statement about omitting the 'read' parameter, but the schema covers that, and the absence of an output schema is mitigated by the 'canned acknowledgment' statement.
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 100% for both parameters, so the description adds minimal value. It does contextualize the interaction (prompt/options) but does not enrich the parameter meanings themselves beyond the existing schema 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 clearly states a specific action ('Walk through the temperature check interaction') and the resource ('demo contact'), making its purpose unmistakable. It also differentiates from sibling tools by emphasizing the demo-only nature and that nothing is saved.
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 when to use it: for demonstrating the temperature check loop, not for real interactions, by explicitly stating 'without saving anything' and 'canned acknowledgment.' It does not mention alternatives, but the demo context is clear enough for an agent to discriminate from other tools.
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.
The tools are mostly distinct: list_demo_contacts retrieves the book of business, get_contact_profile provides the full profile, get_radar returns the radar widget data, draft_as generates outreach, and demo_temperature_check is an interactive walkthrough. However, brief_me and get_contact_profile both include summaries and cadence notes, which could cause initial confusion even though brief_me is specifically for pre-interaction prep.
All tool names use lowercase with underscores, but the verb conventions vary: get_ and list_ are used for retrieval, while brief_me, draft_as, and demo_temperature_check use imperative or verb-particle forms. This is not chaotic, but lacks a uniform verb_noun pattern.
With six tools, the server is well-scoped for a demo application. Each tool covers a distinct aspect of the demo workflow—listing contacts, viewing profiles, inspecting radar graphs, generating briefs, drafting messages, and simulating temperature checks—without redundancy or bloat.
The tool set thoroughly covers the core capabilities of the Centric demo: viewing contact lists, profiles, radar visualizations, interactive briefs, drafting, and temperature check loops. The intentional demo-only nature (no send/update) means no obvious workflow dead ends exist for the stated purpose.