clouddlp_incident_matches

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

readOnlyHint=true already declares this is a safe read, so the '[READ]' prefix adds nothing. Beyond that the description discloses no behavior at all: no pagination or truncation behavior tied to the limit default of 100, no indication of what a 'violating component' contains, and no volume expectations. With no output schema, that burden falls on the description and it is unmet.

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?

It is a single short sentence with no filler, so it is concise, but the '[READ]' tag is redundant with readOnlyHint and consumes part of an already minimal description. Brevity here comes at the cost of underspecification rather than from tight editing.

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 tool with no output schema, no parameter documentation, and a limit parameter that governs result size, the description leaves too much unknown: what a match record looks like, whether results are capped, and how this relates to the incident listing tool. Only the read-only nature is adequately conveyed, and that comes from annotations.

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 carry parameter meaning and it largely does not. 'For an incident' weakly ties to incident_id (already marked required in the schema), but the limit parameter — including its default of 100 and whether it caps or paginates results — is never mentioned anywhere.

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 gives a verb ('Read') and a resource ('violating components for an incident'), so the general intent is inferable, but 'violating components' is vague — it never says these are incident *matches* (the DLP findings tied to an incident), nor how they differ from clouddlp_incidents, which lists the incidents themselves. An agent can guess the relationship, but only by reading the tool name.

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 guidance and no mention of any alternative. Nothing tells the agent to call clouddlp_incidents first to obtain an incident_id, or when to prefer this over any sibling tool. Usage is only implied by the word 'incident'.

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