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

Annotations already mark the tool read-only, idempotent, and non-destructive, so the description adds value beyond that by disclosing the routing-matrix provenance, the real-price guarantee, default line-item inclusion, and the precise error behavior (listing valid ids). These details materially shape how an agent should handle failures and set expectations.

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 three sentences, each carrying a distinct purpose: core behavior/output, input handling and error protocol, and next-step routing. It is front-loaded with the most important resolution logic and contains no filler or redundant restatement of the tool name.

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 absence of an output schema, the description tells the agent exactly what to expect (matched package(s), real prices, default line items) and how to respond to bad input. It also supplies the relationship to neighboring tools, making the tool's position in the overall flow clear without needing extra documentation.

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 input schema fully describes all three parameters and references get_partnership_options for goal and budget ids, so baseline is 3. The description adds a crucial normalization rule—map free-text answers to the closest valid id—and clarifies what happens on invalid input, which goes beyond static schema types and helps the agent invoke the tool correctly.

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 names a specific operation ('Resolves goal + budget'), the underlying resource ('ELC's own routing matrix'), and a concrete return value ('matched package(s) with real prices and their default line items'). It also differentiates from siblings by pointing to customize_package and request_offer as downstream actions rather than competing alternatives.

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 gives clear operational guidance: map free-text answers to valid ids, and if input is bad re-ask rather than guessing. It also states which sibling to use next depending on whether line items need toggling or the offer should be sent as-is. It lacks an explicit 'when not to use this tool' statement, but the context is strong enough to make routing decisions.

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