filter_opportunities

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it discloses that Capsule's API does not support ad-hoc sort and provides a workaround based on monotonic IDs. This goes beyond annotations without contradicting them.

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 a bit lengthy but each sentence carries weight: purpose, differentiation, and the sorting workaround are all essential. It front-loads the purpose and usage guidance, then provides the advanced tip. No filler or redundancy.

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 tool with multiple conditions and a known sorting limitation, the description covers the most critical missing piece (sorting workaround) and gives a concrete example. It doesn't mention pagination or return format, but since there is no output schema and readOnly annotations cover side effects, this is adequate. The 'all conditions ANDed' is already in the schema.

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 50%; the schema itself has detailed descriptions for the conditions array (field, operator, value). The description adds an explicit example of a date filter for 'most recent X' and clarifies the field-name mapping (e.g., response.createdAt vs filter-side 'addedOn') indirectly via the example. This compensates for the partial coverage and adds practical semantics.

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 filters opportunities by structured conditions, listing the key fields (milestone, value, close date, tags). It explicitly differentiates from search_opportunities by naming the sibling and giving example queries that should use this tool, making its purpose unambiguous and distinct.

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 directly says 'Use this — not search_opportunities — for questions like ...', providing explicit when-to-use guidance and naming the alternative. It also explains how to handle the lack of ad-hoc sorting, which is a practical usage note beyond basic selection.

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