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

Annotations already mark this readOnly/non-destructive, so the safety bar is covered. The description adds genuine behavioral context beyond that: newest-first ordering, exclusion of pre-acquisition records unless include_history is true, and cursor-based pagination.

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?

One dense but well-ordered paragraph: what the feed contains, then filtering, then history semantics, then pagination. Front-loaded and each clause carries information, though it is close to paragraph-length.

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?

An output schema exists, so return values need not be explained. Filtering, history scope, and pagination are all covered, leaving only minor gaps such as default date span or ordering tie-breaks.

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 83%, so the schema already documents most parameters. The description adds meaning the schema does not: the comma-separated prefix rule ('a prefix ends in .') and the semantic categories that kinds can take, which helps an agent pick values.

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 specific verb and resource ('Get a portfolio's event feed') and enumerates the event categories returned (value moves, flight activity, registration changes, listings, incidents, web mentions, LTV crossings). This clearly distinguishes it from sibling list tools like get_portfolio_aircraft or list_portfolio_aircraft.

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?

Explains the two filtering axes (kinds prefixes or line_id) and the include_history condition with its default-off behavior. It gives clear context for use but never names an alternative sibling tool or states when-not to use this feed.

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