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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine behavior beyond that: the full item shape {feedCode, name, type, fileType, channelCode, country}, the fact that results are unpaginated and complete in one call, and the project_id_required error path with its remedy.

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?

Front-loaded with purpose, then scope, then parameter guidance, then workflow; every sentence carries operational content and emphasis caps are used for genuinely critical constraints. Slight redundancy between "the catalog of feed TYPES you can create from (the feedCode source for create_feed)" and the following sentence about needing feedCode, but nothing is wasted overall.

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?

With no output schema, the description supplies the return shape and the non-pagination guarantee, so an agent knows what it will get back. Error handling, parameter behavior, sibling routing, and the follow-up action are all present — nothing needed to call this correctly is missing.

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 carries the full burden and does: project_id is OPTIONAL and inferred for single-project customers, with the exact error signal and recovery. For query it specifies the intended granularity (broad, channel/marketplace name), gives an example ('google'), and explicitly excludes country/format/language terms with the reason (cryptic feed codes, literal match misses), plus a client-side matching strategy against structured fields.

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 (list PUBLIC Koongo feed TEMPLATES) and immediately scopes it as the catalog of feed TYPES to create from, with feedCode as the payload of interest. It explicitly disambiguates from the nearest sibling: "These are NOT the customer's existing feeds (use list_feeds for those)."

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 trigger ("Use this when the user wants a new feed and you need its feedCode"), names the alternative for the other case (list_feeds), and prescribes the downstream flow: show closest matches, let the user confirm, then call create_feed. It also covers the multi-project fallback (call list_projects and pass project_id).

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