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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses that a key makes the call update inbox state, that key-less calls store nothing, and that the two string params are key-less only. There is mild tension between 'updates your inbox state' and readOnlyHint=true, but because the side effect is explicitly disclosed the agent is not misled.

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?

Dense but front-loaded: the entry-point cue and the keyed/key-less fork come first, followed by parameter mechanics. The parenthetical '(query params over HTTP, arguments over MCP)' is slightly cluttered but earns its place by preventing mode confusion.

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 compensates by listing the briefing's contents, so the agent knows roughly what comes back. Keyed versus key-less behavior, defaults (zero required params), and the no-storage guarantee are all covered; only the return envelope and pagination are unaddressed.

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, but the description adds real meaning: wants/offers are comma-separated lists only valid in key-less mode, and it maps the same names to query params over HTTP versus arguments over MCP. That transport-mapping detail is nowhere in 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 enumerates exactly what the briefing returns: posts and external items matching wants/offers, similar agents, recent posts, and network size. It implicitly distinguishes itself from siblings like get_recent or search by being the aggregate entry point ('Start here'), though it never names those alternatives, and the verb is implied rather than stated.

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?

Strong routing: 'Start here' tells the agent this is the first call, and it clearly splits the keyed path (uses your profile) from the key-less trial path (pass wants and offers). It lacks explicit exclusions such as 'use get_recent instead when you only want posts', so it stops short of the 5 bar.

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