report

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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds one genuinely useful behavioral fact beyond that: share=true emits anonymous markdown suitable for pasting into a GitHub device report, which signals what data is exposed. It does not explain the baseline window, output shape, or what happens when no prior state exists.

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 core purpose and followed by the one parameter behavior that matters. No filler, though the terseness borders on under-specification rather than tightness.

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 reporting tool with no output schema, the description should say what is being compared (device state before vs. after what operation) and when a valid baseline exists. With two params fronted by the opaque name "report", an agent cannot confidently choose this over list_changes or drift from the definition alone.

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 50%: device is documented in the schema, share has no type-level description. The description compensates for share by explaining that share=true produces anonymized markdown rather than raw data, which is real added meaning. It says nothing about the default when share is omitted, which is the main remaining gap.

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?

"Before/after summary" names an output shape (a diff-style summary) rather than a concrete verb+resource, so the agent must infer that this summarizes device changes. It is not clearly distinguished from siblings such as list_changes, drift, or playbook, which plausibly produce related summaries. Adequate but vague.

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?

There is no when-to-use / when-not-to-use guidance and no mention of the prerequisites that make a "before/after" summary meaningful (i.e., that a baseline must already exist). The only contextual statement is about the share parameter. Alternatives like list_changes and drift are never referenced.

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