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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuinely new context: it requires a TechFabric engineer's Microsoft sign-in with the blog.write scope, it is deterministic with no model involved, and it excludes links the post already contains. The auth requirement and determinism claim are not in the structured data and matter for calling it.

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?

Everything is crammed into one rambling, unpunctuated-in-places paragraph that opens with an auth prerequisite before stating the purpose. Every clause carries information, but the core function is buried mid-sentence and the grammar is awkward, hurting scanability.

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?

An output schema exists, so return shape need not be explained. For a no-required-parameter, side-effect-free lookup, the description covers auth, input modes, determinism, the no-duplicate-links guarantee and the topics-only mode — an agent has enough to call it correctly.

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 explains id, post and markdown. The description still adds meaning the schema does not: that supplying nothing yields topics only, and that markdown with an id overrides the draft's saved text. That empty-args semantics is real added value above the baseline.

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: it returns the internal pages a draft/post should link (with why and where) plus open searches that match the user's work. The two-part output is clear and no sibling tool in the list does the same thing, but the phrasing is convoluted ("the pages of ours a draft or post should link") and never contrasts itself with neighbors like check_draft or get_brief.

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 gives concrete invocation modes — send markdown, an id for a draft, a post URL/slug, or nothing at all for topics only — which is useful routing. However it never says when to use this instead of the adjacent tools (check_draft, check_outline, review_before_publishing) or any exclusion, so the when-to-use decision remains inferred.

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