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

Annotations already cover the read-only, idempotent, non-destructive, closed-world profile, yet the description adds substantial behavioral context on top: page-based totals, totalCapped meaning a lower bound above 500 matches, tabCounts being unnarrowed by filters except listId, and an explicit prompt-injection warning that titles, summaries and viewer-supplied text are untrusted. Date semantics are spelled out (bare date = whole workspace-local day, Z/offset = exact instant, answer's dateRange reports what was used).

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?

It is one undifferentiated wall of text with no line breaks or grouping, and it repeats itself: the per-recipient tracked-link explanation appears in the first sentence and again in 'A drop goes to people picked for it (contactIds)...'. Large portions re-state parameter meanings already documented at 100% coverage in the schema (status, sender, ownerId, listId, contactId, templateId, order, dates), which dilutes rather than adds.

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?

There is no output schema, so the description carries the full burden of describing results, and it does: row fields (template, lists, contactIds, target, owner, visibility, state, sender, counts including needsYou/failed/waiting), createdBy with name/via/agent and 'Former member', tabCounts, totalCapped, match objects and dateRange. An agent could parse the response without a return-type schema.

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 already 100%, so the baseline is 3, but the description earns more by explaining interactions the schema cannot: tabCounts ignores the narrowing filters except listId (tabCountsFilter = listId), a query of three or more letters re-sorts by best match and attaches match { in, snippet, name }, and a sent range excludes drops that were never sent. These are real semantics, not restatements of field types.

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 concrete definition of a drop (one email template sent from the member's Gmail, with per-recipient tracked links) and then states the verb and resource: list the workspace's drops a person can see, one tab at a time. It is unmistakably a paged list operation, but it never distinguishes itself from the sibling lnkdrp_list_campaigns, which the parenthetical 'campaigns in the API' actively invites confusion with.

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 clear operating context: default tab is active, defaults for order differ depending on whether a query is present, and the tool is available on every plan. It also flags edge behavior ('A list this person cannot open gives an empty page', 'Another person's private drop is not listed'). It stops short of explicit when-not guidance and never names an alternative such as lnkdrp_get_drop for a single drop or lnkdrp_list_campaigns.

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