compare_entities

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

Annotations already declare read-only, idempotent, non-destructive behavior, but the description adds substantial behavioral detail beyond them: the 10×10 cap, the 422 failure mode, consolidated-only values, one value per (entity, hub, year), fiscal-year alignment, and the caveat that non-December filers may see different values here than from get_fact. These are exactly the operational traits an agent needs before invoking the tool.

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 front-loaded with the core purpose, then moves efficiently through limits, tool preference, return shape, and the fiscal-year nuance. Every sentence adds useful information, and the line breaks make it easy to scan.

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?

Given the existence of an output schema, the description need not explain return values, yet it still summarizes the return shape (one row per entity plus a cells map) and the key fiscal-year caveat. Combined with the cap and failure-mode disclosure, it provides enough context for correct invocation in this complex comparison tool.

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 carry parameter meaning. It adds useful semantics for the key parameters: entity_ids and hub_concept_codes are bounded by the N=10/M=10 limits, fiscal_year is tied to fiscal-period alignment and FY forcing, and hub_concept_code keys the output cells. It still does not explicitly describe the expected string format of entity_ids or hub_concept_codes, and fiscal_period_type is only implied via 'FY forced,' but the core meaning is well beyond what the bare schema provides.

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 opens with a specific verb and resource: 'Build a comparison matrix for N entities × M concepts at one period.' It distinguishes itself from sibling get_fact by name and explicitly states the preferred use case, so an agent can tell exactly what it does and when it is the right tool.

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?

It gives an explicit selection rule: 'ALWAYS prefer this over N×get_fact when comparing more than one company.' It also discloses the operational cap (N=10, M=10) and the failure mode (422 validation error), which is direct guidance for avoiding misuse.

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