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

With no annotations provided, the description carries the full transparency burden and does a reasonable job: it discloses the bounded nature of the decoded sample, that the bound is stated in the reply, that the tool follows a moving head, and that it is not pinnable. It does not cover error behavior, authentication, or side effects, but for a read-oriented coverage view the key behavioral traits are disclosed clearly.

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 efficient: it front-loads the main purpose, then lists the concrete output components in a compact sequence, and closes with the two key limitations. Some jargon like 'KVs cursor bucket' and 'bond stream' is not expanded, but every sentence contributes distinguishing information.

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 low-complexity tool with one optional parameter and no output schema, the description is largely sufficient: it enumerates the output categories, explains the discovery mechanism, and states the bounded and non-pinnable behavior. It does not describe the reply format or failure modes, but those are less critical given the tool's read-like purpose and the schema's parameter documentation.

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 schema already documents the single optional parameter cursor_sample as a decimal string up to 1024 and notes the bound appears in the reply, so schema description coverage is 100%. The tool description adds no extra meaning to this parameter, which keeps this at the baseline rather than higher.

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 identifies the tool as producing fleet-wide mining coverage from the KV cursor bucket, with specific countable outputs: shard cursor counts per target/cell, a bounded decoded sample, and bond stream message counts. It also distinguishes itself by noting it is roster-free and not pinnable. However, there is no explicit action verb like 'returns' or 'reports,' so it stops short of the clearest possible formulation.

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 useful context about when this tool is appropriate: it is roster-free, discovers cells from subject writes rather than a table, and follows the moving head. It also states explicit limitations ('not pinnable, and says so'), which helps an agent avoid using it when pinned or roster-based data is needed. It does not name alternative sibling tools or give an explicit 'use this tool when...' rule, so it misses the top score.

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