evaluate_portfolio_alignmentCompare a clean mandate with normalized holdings. Do not send PDF, CSV, spreadsheet, or factsheet files; extract them before calling.
| Name | Required | Description | Default |
|---|---|---|---|
| rules | No | ||
| mandate | No | ||
| holdings | Yes | ||
| base_currency | No | USD | |
| portfolio_name | No | Portfolio | |
| idempotency_key | Yes | ||
| source_warnings | No | ||
| composition_scope | No | unknown |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate idempotency and non-read-only behavior. The description adds context about input normalization and file extraction, but does not disclose other behavioral traits such as side effects, rate limits, or error scenarios. It does not contradict annotations.
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 long, front-loaded with the core action, and contains no redundant information. The inclusion of the file-handling instruction is relevant and concise.
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?
Despite having a rich schema with nested objects and an output schema, the description is too minimal. It does not explain the tool's overall workflow, how parameters like rules or composition_scope affect the evaluation, or any prerequisites beyond normalization. The output schema covers return values, but input semantics and invocation context are largely missing.
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 for parameter meanings. It only hints at 'mandate' and 'holdings' through the phrase 'clean mandate with normalized holdings', but gives no detail on idempotency_key, base_currency, rules, or other parameters. This is insufficient for a tool with 8 parameters.
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 states a clear action ('Compare a clean mandate with normalized holdings') with specific resources (mandate and holdings). While it doesn't explicitly differentiate from the sibling tool calculate_portfolio_constraints, the purpose is unambiguous and not a tautology.
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 a clear prerequisite ('clean mandate with normalized holdings') and an explicit exclusion ('Do not send PDF, CSV, spreadsheet, or factsheet files; extract them before calling'). However, it does not mention when to use this tool over the sibling calculate_portfolio_constraints, so guidance is partial.
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.
Each tool targets a clearly distinct task: one performs deterministic arithmetic checks on holdings, the other evaluates semantic alignment against a mandate. Their purposes do not overlap, and the descriptions explicitly warn against confusing them.
Both tool names follow a consistent verb_noun pattern (calculate_portfolio_constraints, evaluate_portfolio_alignment), using clear action verbs and domain-specific objects. The naming is uniform and predictable.
With only two tools, the server feels minimal for the PortfolioFit domain. While each tool serves a specific purpose, the set is at the lower boundary of what is considered reasonable, making it borderline acceptable.
The core workflow of calculating constraints and evaluating alignment is covered, but the server relies on external preprocessing of holdings and mandates. Minor gaps exist, such as the lack of a tool to interpret natural-language mandates or extract data from files, but these can be worked around.