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

Goes well beyond the destructiveHint=true annotation by naming the cascade (all client grants destroyed), the external impact (existing shared links break for holders), the permanence of deletion, and the ownership authorization requirement. This is exactly the extra context a mutation tool needs.

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?

Three tight sentences with the destructive effect front-loaded, followed by the authorization constraint and the id-lookup hint. No filler and no repetition of the 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?

With an output schema present, return values need no explanation, and the annotations already cover the safety profile. The description supplies the remaining essentials: cascade scope, irreversibility, ownership gate, and id provenance.

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 0%, so the description must carry the load. It tells the agent where the reportId comes from (list_shared_reports) without restating the raw name, but does not describe the expected format or what happens on a malformed/unknown id.

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 (permanently deletes) and resource (a saved shareable report) and quantifies the effect: every client grant is removed and the shared link breaks. This clearly separates it from siblings like delete_saved_filter, delete_content_group, and delete_annotation.

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 precondition (only reports owned by the authenticated user) and routes the agent to list_shared_reports for obtaining the id. It lacks an explicit when-not-to-use case (e.g., revoking access for one client via manage_report_access), but the context is otherwise unambiguous.

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