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

The annotations already carry the safety profile (readOnlyHint=false, destructiveHint=true, openWorldHint=false), so the description only needs to add context. It does add two valuable facts: an act key is required, and each result is processed independently ('Each result stands alone; the answer says what was kept for each'), implying per-item acceptance. It does not explain what destructiveHint means here — whether re-marking a place overwrites a prior outcome — which is the single most important behavioral question for a destructive tool.

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?

All content is relevant, but the opening is one long run-on sentence built from nested parentheticals, which makes the critical payload rules harder to scan. 'Each result stands alone; the answer says what was kept for each' is close to redundant with the schema's per-item note, and the act-key requirement is buried at the end instead of being front-loaded.

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 two-parameter, no-output-schema mutation tool this is adequate: the outcome vocabulary, the input source (listings_read) and the auth prerequisite are all present. What is missing is any statement of what the call returns and whether repeated marks are idempotent or overwrite prior outcomes — meaningful gaps given destructiveHint=true.

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 the schema already defines project, results, directory, outcome, url and where. The description adds only a little beyond that: it reinforces that directory is 'its name from listings_read' and restates the outcome meanings in plain prose. Baseline 3 is correct since the schema is doing the heavy lifting.

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 names the resource (directory listings) and enumerates the exact outcome vocabulary the tool records (submitted / listed / stopped / not_for_us), which tells an agent precisely what this call does at the payload level. It falls short of 5 because the verb 'Reports back on' reads like a read operation, while the annotations declare destructiveHint=true; the agent must infer from 'the answer says what was kept' that this persists state rather than just fetching it.

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?

It gives one useful routing cue: the place name must come from listings_read, and it states the prerequisite 'It needs an act key'. However, there is no explicit when-to-use versus when-not, no statement that this is the write counterpart to listings_read, and no guidance on call frequency or batch size ('many in one call' is vague). Usage is implied rather than prescribed.

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