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

Beyond destructiveHint=true, it reveals irreversibility ('permanently'), the refusal guard for keywords with generated articles, and a nontrivial side effect: scheduled articles targeting deleted keywords are kept and their ids returned for headline regeneration. This is meaningful behavioral context absent from structured metadata.

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?

Four sentences, each carrying information: the destructive action, the refusal condition, the side effect on scheduled articles, and the website_id guidance. It is front-loaded and has no filler.

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?

Given annotations, a full input schema, and an output schema, the description covers the key operational details an agent needs: what gets deleted, when the call is rejected, and what happens to scheduled articles. No critical calling behavior is left unexplained.

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 100%, so the baseline is 3. The description adds only a slight reminder to pass website_id in multi-website accounts, mirroring the schema's own note, and provides no additional meaning for keyword_ids beyond what the schema already states.

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 opens with 'Permanently deletes keywords from the website,' a specific verb+resource action that clearly separates it from siblings like add_keywords and delete_scheduled_article. The scope and irreversibility are explicit.

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?

It states when to pass website_id ('when the account has several websites') and gives an explicit when-not condition: the call is refused if any keyword already has a generated article. It does not explicitly name alternative tools for those blocked cases, so it stops just short of perfect routing guidance.

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