List B2match notifications

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

This is exactly the behavior structured fields cannot convey: fetching the list resets the unseen counter to 0 even though the client never sends ReadNotification, while the unread counter is unchanged. The annotations (readOnlyHint=false, idempotentHint=false) are consistent with that disclosed side effect, and the description explains the gating env var. That is high-value, non-redundant disclosure.

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?

Four short sentences, with the default behavior and the counter-reset side effect front-loaded ahead of the env-var gating. Every sentence carries functional information. The parenthetical aside about never sending ReadNotification is slightly dense on first read but justifies its place by explaining why the reset is surprising.

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 four-parameter read-with-side-effect tool with no output schema, the description covers return semantics (counters vs full list), the hidden mutation, and the precondition for the full fetch. It doesn't describe pagination behavior or what fields the full notification list returns, minor gaps given the schema documents the cursor and page size.

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 schema already documents event, first, after, and acknowledge_marks_seen, including the cap of 50 and the side-effect coupling. The description adds only a restatement of the acknowledge_marks_seen requirement, which the schema already states nearly verbatim. Baseline 3 applies since the schema does the heavy lifting.

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 resource and behavior: it returns unread/unseen notification counters by default, and can return the full notification list under a condition. It is unambiguous about what the tool yields, though it never states the plain verb 'list notifications' and instead leads with the default mode. No sibling in the provided list overlaps with notifications, so no differentiation is needed.

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 clearly splits the two modes of use: default call gives counters only, and the full list requires B2MATCH_ALLOW_SIDE_EFFECT_READS=1 plus acknowledge_marks_seen=true. It warns of the consequence of choosing the full-list mode (unseen resets). It stops short of stating when an agent should prefer one mode over the other or what to do when the env var is unavailable.

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