mdl_feeds_delete

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely new context beyond that: host-configured MyDramaList authentication is required, and the operation mutates remote state. It stops short of stating reversibility or side effects on feed contents.

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 short, front-loaded sentences; the action comes first and each sentence adds a distinct constraint (auth, mutation, gating). No filler or repetition, though the telegraphic 'Feeds: delete.' fragment is slightly clinical.

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 destructive, non-idempotent tool with no output schema, the description covers the essentials an agent needs before calling (auth requirement, caution, explicit-request gating). It omits what actually gets destroyed, whether the action is reversible, and how to source the feed_id, leaving clear gaps.

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% and the description says nothing about feed_id — neither its semantics nor where an agent obtains one or whether a numeric ID and a slug are equivalent. The schema types the value (integer > 0 or a 1-128 char slug pattern) but carries no meaning the description fills in.

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 ('delete') and resource ('Feeds'), which cleanly separates it from siblings like mdl_feeds_create, mdl_feeds_edit and mdl_feeds_hide. It does not explain what a 'feed' is or what deletion implies, so it is clear but thin rather than fully distinguishing.

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 gating condition: 'use only for an explicit user request,' which is real when-to-use guidance for a destructive call. It does not name alternatives such as mdl_feeds_hide for non-destructive removal, so it stops short of a full alternative map.

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