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

Annotations only give a coarse profile (not read-only, not idempotent, not destructive); the description adds far more: the required inbox:write scope, that the first call is a validation dry run that changes nothing, that unknown fields are refused by name, and that a human must approve the summary before the second call. The only gap is post-success behavior, which is not described and has no output schema to fall back on.

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?

Short and front-loaded: the permission requirement and the two-call shape come first, then the sequencing rule. The telegraphic fragments ('Two calls. Needs inbox:write.') are terse but readable, with no filler sentences.

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?

For a mutation tool with no annotations detail beyond hints, no output schema, and 33% schema coverage, the description covers the confirmation protocol but not what up_to_seq means, what the summary actually contains, or what the second call returns on success. An agent would still have to guess at a required parameter's meaning.

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 only 33% – only confirm_token is documented in the schema, and the description usefully reinforces its two-call lifecycle. However, up_to_seq has no type and no explanation anywhere, and conversation_id is likewise undefined, so the description fails to compensate for the low coverage on the two required parameters.

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 ('Mark a conversation read') that matches the title and is unambiguous. It does not differentiate itself from nearby siblings such as get_conversation or list_messages, but no sibling claims the same action, so confusion risk is low.

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?

The description gives a clear procedural rule for the two-call pattern and when to make the second call, which is genuinely useful. It never states when to use this tool rather than alternatives (e.g., reading a conversation with get_conversation instead), so alternative selection is left to inference.

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