Calculate how much time and money a real estate agent saves switching to PrimaCoda.
Args:
deals_per_month: Number of transactions the agent closes per month.
current_method: "human_tc" or "diy"
| Name | Required | Description | Default |
|---|---|---|---|
| current_method | Yes | ||
| deals_per_month | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only describes the calculation function. It does not mention that this is a read-only operation, potential limitations, or any side effects, leaving the agent to infer safety.
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 with a clear purpose and a structured parameter list. Every sentence provides necessary information without repetition.
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 core purpose and parameter meanings, but does not provide usage context or clarify what the output represents, though an output schema exists. Given the tool's simplicity, it is minimally sufficient but lacks the contextual guidance expected for full completeness.
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?
The description includes an Args section that explains each parameter beyond the schema. It defines deals_per_month as transactions per month and lists the two allowed strings for current_method, compensating for the 0% schema description coverage.
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 calculates time and money savings for a real estate agent switching to PrimaCoda. It uses a specific verb and resource, distinguishing it from qualitative tools like is_primacoda_right_for_me.
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 no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or suggest switching to is_primacoda_right_for_me for qualitative assessments.
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 have clearly distinct purposes: deadline listing vs. recalculation, motion drafting vs. status polling, and product info vs. fit assessment. However, primacoda_info with topic 'comparison' and is_primacoda_right_for_me could both be used for fit/plan questions, and the mix of legal, real estate, and sales tools may cause occasional misselection.
The majority of tools follow a clear verb_noun pattern (e.g., calculate_savings, draft_motion_from_matter, list_my_deadlines). Two exceptions stand out: primacoda_info is a noun phrase without a verb, and is_primacoda_right_for_me is a question-style name, deviating from the established convention.
With 11 tools, the count sits comfortably in the ideal range (3-15). Each tool serves a distinct function, and the number feels appropriate for a server that covers legal drafting, deadline management, contract extraction, and sales/product information.
The server covers core workflows: drafting/polling motions, listing/recomputing deadlines, extracting contract data, and handling leads/product info. However, there are notable gaps; despite the 'transaction-coordinator' name, there are no tools to list, create, or update transactions or matters directly, and lead management beyond recording is absent.