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

With no annotations, the description carries the full behavioral burden and does disclose one genuine trait, the requirement of a key. It says nothing about visibility defaults, idempotency, or what a re-save does, which is thin for a creation 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?

Compact and front-loaded, opening with the core action before the field hints. The clause-heavy second half is dense but every clause maps to actual schema fields, so little is wasted.

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?

A 16-parameter creation tool with no annotations and no output schema needs more than three field hints. Spatial parameters (lat/long/bbox/radius), sort, unit, public, enrichers, and the required collection go unaddressed, leaving the agent to rely entirely on 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 88%, so the schema already documents most parameters; the description largely paraphrases it ('q is a text match', 'Sources, kinds and tags narrow'). It does add meaning for upcoming, which the schema leaves undocumented. Baseline 3 fits given the high coverage.

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 concrete verb+resource: 'Save a query as a feed'. This clearly separates it from list_feeds, feed_items, and follow_feed. However, it never distinguishes itself from the close sibling submit_feed, so full marks for differentiation are withheld.

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?

Usage is only implied: '(needs a key)' signals an auth prerequisite, and the field hints imply query-shaping. There is no explicit when-to-use guidance nor any statement of when to prefer submit_feed or follow_feed instead.

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