prune_candidates

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 so well: it discloses that the tool deliberately returns evidence rather than actions, that buckets encode recommended actions, and that pages absent from the report were absent from Search Console. It does not discuss rate limits, auth, or scoping behavior for site/engine, leaving minor gaps.

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-loads the purpose, then uses a bulleted bucket list that maps cleanly to the tool's output. Every sentence earns its place and the structure makes the taxonomy scannable. No redundant restatement of the name or title.

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 read-only analysis tool with an output schema, the description covers what an agent needs: the classification logic, the action implied by each bucket, and the boundaries of its conclusions. Return values are covered by the output schema, so the description need not restate them.

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 must compensate, but it explains only `days` (the reporting window). The other three parameters (`site`, `engine`, `max_pages`) are never mentioned, so an agent gets no added meaning for them beyond the schema's bare titles and defaults.

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 ('classify pages by measured traffic') and frames the tool's role as pre-pruning triage. The bucket taxonomy and the explicit note that it is not a delete list distinguish it sharply from generic traffic tools like traffic_drops or page_analysis. An agent knows exactly what this tool produces.

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 clear context for invocation ('before any pruning decision is taken') and routes the agent to complementary tools ('Pair with content_quality and internal_links_audit before acting'). It also warns what not to conclude (no delete list; absent pages are a crawling question). It stops short of naming a true alternative tool that would replace it, so it is strong but not fully exhaustive.

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