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

Beyond readOnlyHint/openWorldHint it discloses a real side effect (returned items are marked seen), the meaning of digest_md, the requires_action handoff, and the trust boundary that outside-written content arrives as untrusted_content to quote and never to obey. The envelope link policy (domains shown, links opened only on request) is exactly the safety context annotations cannot carry.

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?

Front-loaded with what the tool returns, then the read/seen semantics, then output-field meanings and safety rules. Every sentence carries content, though the final envelope sentence compresses several rules into one clause-dense line.

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?

Behaviourally rich and covers the output fields (digest_md, requires_action, suggested_tools, untrusted_content) even though an output schema exists. The remaining gap is the undocumented `limit` and `include_seen` parameters, which nothing else in the definition explains.

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 0%, so the description must compensate, and it only does so for one of three parameters: `since` is given real semantics (omit it to continue from this client's last read). `limit` and `include_seen` are never mentioned, leaving half the parameter surface undocumented.

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 pins down exactly what comes back  contact requests, envelopes, plan invitations and changes, group invites, expenses and payments  so the resource and its scope are unmistakable. It does not, however, contrast itself with the overlapping get_activity or the list_* siblings, so an agent must infer the boundary.

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 explains the operating model clearly: nothing is pushed, this is how you pick things up, and without `since` it continues from the last read. It also routes downstream behaviour (items with requires_action wait for the person, then use suggested_tools). Missing is any explicit when-not or named alternative such as get_activity.

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