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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so mutation status and open-world behavior are covered structurally. The description adds meaningful state-chaining context ('returns feed_id', data mode consumes feed_id/dataset, build produces a blueprint) but says nothing about whether re-running feed mode overwrites prior output, what sources must be connected first, or what the returned dashboard actually contains.

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 mode-first structure is front-loaded and the per-mode clauses are telegraphic with no filler sentences. It is dense to the point of clipped grammar, but every phrase carries a required-input or output fact, so nothing 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?

For a 15-parameter, nested-object, multi-mode tool with an output schema, the description supplies what the structured fields cannot: which mode to pick and which inputs each mode demands. Remaining gaps (how the three modes interact across a session, what the feed/dashboard delivers in practice) are modest given the output schema and high schema coverage.

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 93%, so the baseline is 3, and the description clears that bar by mapping parameters to modes (feed needs url, data needs feed_id and dataset, build needs feed_id) - a cross-parameter dependency the flat schema with no required fields cannot convey. It adds nothing about the many remaining optional parameters (from/to, pages, replace, sources, bigquery, memory_key), which the schema mostly documents on its own.

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 leads with a concrete verb+resource ('daily SEO data feed for key pages and a live dashboard in the chat') and then decomposes the tool into three named modes with distinct deliverables, which is well beyond a restatement of the name. It never distinguishes itself from plausible siblings like watch or site_audit, so an agent still has to guess whether this is the right entry point within the suite.

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?

'Pick with mode: feed = ... data = ... build = ...' is explicit routing guidance and is reinforced by naming the required inputs for each branch, which the schema cannot express since zero parameters are marked required. There are no when-not conditions or pointers to alternative sibling tools for overlapping tasks such as tracking or auditing.

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