peer_comparison

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds real behavioral context beyond the readOnly/openWorld annotations: partial results are surfaced ('Failed tickers are reported, not dropped silently') and the response deliberately omits score components and their inputs, pointing elsewhere for those. It stops short of describing output layout or latency/cost characteristics, which matters somewhat given there is no output schema.

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?

Four short sentences, front-loaded with what the tool returns and its scope, then failure behavior, then the sibling route. Every sentence carries a distinct, non-redundant fact.

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 one-parameter, read-only, open-world tool with no output schema, the description covers scope, cardinality, partial-failure handling, and sibling routing. The remaining gap is that it never sketches the shape of the returned comparison (scores vs. ratios, ordering), which an agent must infer.

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 0% and the schema is a bare array of strings with no minItems/maxItems, so the description carries the constraint load: it supplies the 2-10 cardinality bound and the implicit requirement that all tickers belong to one sector. It does not specify ticker format (exchange suffix, case), leaving one residual ambiguity for a single-parameter tool.

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?

States a concrete verb and resource ('Fundamental ratios and scores for several companies side by side') plus the cardinality bound (2 to 10 tickers) and the intended purpose (relative valuation within one sector). It also explicitly contrasts with the sibling fundamental_ratios for the single-company case, so an agent can choose between them without opening either schema.

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?

Gives an explicit use condition ('for relative valuation within one sector') and an explicit alternative ('call fundamental_ratios for one company'), which is the main routing decision for this tool. The 2-to-10 ticker bound further rules out degenerate single-ticker or bulk-universe calls.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.