Slap My Bot

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering the safety profile. The description adds 'do not poll' (a behavioral constraint not in annotations) and 'last observed counts', implying cached/observed data rather than live state. This adds useful context beyond the annotations without contradiction.

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?

Two sentences with no waste: the first lists what it returns, the second gives the usage constraint. The key information is front-loaded and the entire definition is appropriately brief for a simple getter.

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 read-only getter with no parameters and no output schema, the description conveys the purpose and usage condition. It could specify exact field names or return format, but the phrase 'desktop readiness, active window and last observed counts' is sufficient for a diagnostic tool. The sibling set clarifies its role. Minor gap: no mention of what 'counts' refers to, but this is acceptable.

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?

The tool has zero parameters, so schema description coverage is trivially 100%. There is nothing to explain about parameters, and the description correctly focuses on the returned data. The baseline for 0-parameter tools is 4, and the description meets it.

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 it provides 'Desktop readiness, active window and last observed counts' — a clear resource (status) with specific attributes. It distinguishes from siblings (punish_for_mistake, set_slap_enabled) by being a getter, though it doesn't explicitly name a verb like 'retrieve' or 'fetch'. The title 'Check Slap-My-Bot' reinforces the intent.

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?

Explicitly states 'Only use when asked to diagnose; do not poll,' which gives a clear when-to-use condition and a prohibition. It doesn't name alternatives, but the sibling names (punish, set) make it evident this is the diagnostic read tool. The guidance is sufficient for routing.

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

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

The description adds context beyond annotations by stating the tool queues slaps (a side effect) and that work continues after the call (non-blocking). It also implies it is for concrete mistakes only. While it doesn't mention that repeated calls accumulate slaps (non-idempotent), that is already captured by idempotentHint=false. The description adds meaningful behavioral context without contradicting annotations.

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 two sentences, with the core action and trigger front-loaded. The second sentence is a succinct usage note. There is zero fluff or redundancy—every word earns its place.

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?

The tool has 5 parameters, 1 required, and no output schema, with minimal annotations. The description covers the trigger and action, but does not explain the effect of muted, agent_name, or duration_seconds, nor how severity maps to slap count (though that is in the schema). Given the parameter count and lack of output schema, the description is too sparse to let an agent use all options correctly.

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?

The description provides no parameter guidance whatsoever. Schema coverage is only 40% (reason and severity have descriptions), leaving muted, agent_name, and duration_seconds entirely undocumented in both the schema and the description. The description only hints at 'reason' indirectly via 'concrete mistake', but gives no meaning for the other parameters. An agent would have to guess or rely on defaults.

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 action ('Queue automatic desktop slaps') and the exact trigger condition ('when the user points out your concrete mistake or requests a slap'). It clearly distinguishes this from the sibling tools by its core function—it does not toggle enable/disable or query status, but directly queues slaps. The verb+resource is explicit and unambiguous.

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 trigger for when to call the tool (concrete mistake or user request) and an explicit exclusion ('Ordinary messages need no feedback tool call'). It does not mention sibling alternatives, but the trigger itself is sufficient to route an agent. The exclusion is a strong usage signal.

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

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

Annotations already indicate idempotentHint=true and destructiveHint=false, so the description doesn't need to cover those. It adds a meaningful behavioral detail: disabling also closes an active background window. This is beyond what annotations provide and helps the agent anticipate side effects.

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?

Two short sentences, front-loaded with the primary action and a secondary side effect. No wasted words.

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 simple one-parameter boolean setter with idempotentHint and no output schema, the description covers the essential behavior and the notable side effect. It could mention that the current status can be checked via get_slap_status, but that's a minor gap given the tool's simplicity.

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 0%, so the description must compensate. The description explains the meaning of the 'enabled' parameter implicitly: true enables feedback, false disables it. However, it doesn't explicitly map the boolean values to the behavior, leaving some inference required. Baseline 3 is appropriate because the single parameter's meaning is largely inferable from the tool name and description.

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 clearly states the tool's function: enable or disable feedback when the user asks. It also mentions a secondary behavior (closing an active background window when disabling). It distinguishes itself from siblings by focusing on setting the enabled state, though it doesn't explicitly name the sibling for checking status.

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 implies usage: use when the user wants to turn feedback on or off. It doesn't explicitly state when not to use it or mention alternatives like get_slap_status for checking current state. The context is clear but exclusions are absent.

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