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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add operational context — and it does: a fixed 20-result ranked window surfaced via the limited and count_is_exact fields, plus the Linko URL in each result for citation. It omits pagination interaction between limit/offset and that fixed window, which tempers it below a 5.

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?

Four tight sentences, each doing distinct work, with the capability statement first and the caveats after. No filler, though the result-window sentence is slightly oblique in naming fields the agent has not yet seen.

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?

Output schema exists, so return shape needn't be spelled out, and the description still flags the two result-window fields and the citation URL. For a 12-parameter filter tool the description is close to sufficient, missing only parameter-level disambiguation.

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?

With 12 parameters and 0% schema description coverage, the description carries the full burden, and it does map filter groups to parameters (keyword, tag/topic, type, finished, date range, timezone, order). But it never clarifies the subject_id vs subject_name pair, the difference between days_ago and start_date/end_date, accepted date formats, or the order enum values — real gaps at this coverage level.

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?

A specific verb plus a precisely scoped resource ('the linked account's saved resource metadata'), and it enumerates the filter dimensions an agent cares about (keyword, tag/topic, type, completion, saved-date). It also distinguishes the payload from get_resource, so the agent knows this returns metadata, not full text.

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?

Explicitly routes the agent to get_resource when saved source text is needed, which is the most likely confusion. It does not, however, distinguish itself from same-family search siblings such as search, search_notes, and linko_search, so the agent must infer that this one is metadata-only over resources.

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