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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, but the description adds real context the annotations do not: tags are internal-only ("never go to a platform"), published posts are in scope, and there is a 500-post ceiling. It notably clarifies that set with an empty array wipes all tags, a destructive-in-effect case the destructiveHint=false annotation does not signal. It stops short of describing idempotency of repeated add calls or error/partial-failure behavior across a 500-post batch.

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 core verb and scope are front-loaded in the first clause, followed by the workflow and then per-parameter notes, which is a sensible ordering. The sentence is dense with stacked parentheticals ("published posts included (tags never go to a platform)") and the final clause partly repeats what the schema descriptions already say about set.

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 four-parameter batch mutation with no output schema, the description covers what it does, when to use it, which sibling calls to chain, the batch limit, the platform-side-effect boundary, and the empty-array wipe case. Nothing an agent needs in order to call this correctly appears to be missing.

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 100%, so the schema already documents each parameter, making 3 the baseline. The description still earns credit above that by explaining that add/set accept tag names or ids and that an unrecognized name is created as a new tag, and by restating that set replaces a post's tag set wholesale — semantics the schema text does not convey.

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?

Opens with a specific verb triple and resource ("Add, remove or replace the tags of up to 500 posts at once") plus a scope qualifier ("published posts included"). The parenthetical "tags never go to a platform" further pins down what the operation actually touches, and it is clearly distinct from siblings like create_tag, update_tag, and delete_tag.

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 motivating scenario ("tag older posts so get_tag_analytics has enough posts to compare") and a concrete three-step workflow with named siblings: find via list_posts, read captions, then tag. An agent knows both when to reach for this tool and which sibling calls precede it.

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