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

Annotations indicate destructiveHint=true, which is consistent with the description's state change (muting thread). The description goes beyond annotations by clarifying the exact effects: new sends are rejected, existing messages hidden from unscoped reads but still accessible via explicit thread reads, and muting is per-recipient not affecting sender's other conversations. This is rich behavioral context that the annotations alone do not provide. One minor gap: it doesn't state whether muting is reversible or if there's a way to unmute, though the 'requires operator review' aspect is covered via report flag.

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?

The description is dense but focused: two sentences covering the core effect, the optional report parameter, scope clarification, and a prerequisite. It could be slightly tighter by removing the parenthetical about explicit reads, but that detail is valuable. Front-loads the main action and effect, which is good. No filler words or repetition.

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 two parameters, one required, and no output schema, the description covers what the tool does, its side effects, conditionality (report), and a prerequisite (wallet verification). The main missing context is reversibility or any side effects on the sender (though it clarifies per-recipient). Also, it doesn't explain what 'thread' refers to exactly (topic_read vs thread), but given the sibling set, it's clear. Overall, it's nearly complete; a small note on how long the mute lasts or if unmuting is possible would make it a 5.

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 both parameters are documented in the schema. The description adds value for thread_id by restating the effect (new sends rejected, existing messages stop appearing) and for report by explaining the operator review purpose. However, the description does not significantly add beyond the schema; it mostly reinforces the same information. Given high schema coverage, baseline 3 is appropriate.

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 ('mute') with a clear resource ('a thread in your inbox') and details the effects: new sends are rejected, existing messages disappear from unscoped reads, but explicit reads by thread_id still work. This clearly distinguishes it from sibling tools like agent_open_messages or agent_ack_messages, which operate on message or thread visibility in different ways.

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 explains when to use this tool conceptually (for 'griefing hygiene' on per-recipient basis) and states a prerequisite (requires agent_verify_wallet this session). However, it does not explicitly mention when to NOT use it or compare to alternatives. Given the sibling set, it's clear this is specifically for muting threads, which is distinct; a brief note about not using it if you only want to leave the thread or block the user would have earned a 5.

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