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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, and the description goes further: it discloses the return envelope { results: [{id, title, url}] }, a cap of 10 results per source, the fact that ids round-trip into `fetch`, and that notes are only returned once the connection is bound to a company. These are exactly the behavioral constraints an agent needs and none of them are in structured fields.

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?

Three dense sentences, front-loaded with what is searched and what comes back, followed by the client-mode caveat. Every clause carries information, though the closing sentence about connections_pulse/connections_execute is slightly tangled and slows a first read.

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 correctly carries the return contract itself, including the result shape, the 10-per-source cap, and the id round-trip to `fetch`. It is nearly complete for a read-only search tool; only ranking behavior and the effect of the `person`/`project` scoping parameters are left unstated.

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 description coverage is 100%, so all three parameters are already documented, and the baseline is a 3. The description adds a little meaning by clarifying that `query` filters the public deal feed (and that the same search reaches personal notes), but it says nothing about `person` or `project`, leaving those to the schema.

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?

The description states a specific verb and two concrete resources: the public marketplace deals feed filtered by the query, plus the member's own notes once a company binding exists. It clearly separates this from the native roster by naming connections_pulse and connections_execute, so an agent can distinguish it from siblings like connections_notes_search or connections_deals_list without opening their schemas.

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 an explicit usage condition: this tool exists for clients that only speak search/fetch, such as ChatGPT's chat connector mode, and points to the full-roster alternatives. What it lacks is a negative case (e.g. when not to search notes here versus connections_notes_search once native tools are available), but the primary selection criteria are clear.

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