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

With only readOnlyHint available, the description carries most of the behavioral load and does so well: it discloses loose matching, that unmatched posts are verified away and never stored, that some results are stored automatically while read-only agents get unstored results with no object ids, and that discarded_count reports rejections. There is mild tension between readOnlyHint=true and the statement that matches get stored in the user's brain, though that storage reads as a downstream pipeline behavior rather than a mutation of the search target, so it is not a hard contradiction.

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?

Purpose is front-loaded in the first sentence, and the dense block is mostly load-bearing (storage semantics, new/seen split, watcher reporting rule, link syntax). It is long and would benefit from splitting into short cue sentences, but there is little outright waste.

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?

With no output schema, the description fully specifies the response shape (new vs seen, discarded_count, present/absent object ids) and the watcher reporting contract, so an agent knows both what it will get back and what to do with it.

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 baseline is 3; the description goes beyond it by explaining the purpose of found_by_object_id (filing finds under the searching agent), when to omit it, and how returned object ids are meant to be used in [label](object:<object_id>) link syntax.

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 ('Search public LinkedIn posts by keywords') and is immediately distinguishable from siblings like search_tweets, search_linkedin_messages, or search_graph_objects. It also pre-empts the loose-match confusion by explaining the returned set has been keyword-verified.

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 explicit when-to-use and when-not-to-use guidance: do not re-save matches with graph tools, only report/email when 'new' is non-empty as a scheduled watcher, never include 'seen' posts, and omit found_by_object_id in normal chat. These are concrete routing rules an agent can act on.

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