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

Annotations already cover the read-only, idempotent, non-destructive profile, so the description wisely spends its space elsewhere: it discloses that only metadata is returned, that pagination is capped at 50, and that visibility differs for human admins. The main gap is result ordering across pages, which is unstated.

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?

Three short sentences, with the core purpose and the sibling-disambiguation front-loaded. Nothing is padded, though the final sentence about admin visibility reads as an afterthought and could be tighter.

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?

With no output schema, the description should say more about what 'metadata' includes, since an agent cannot infer the returned fields. Pagination and visibility are covered adequately, but the return payload and the offset/result_offset relationship remain underspecified for a four-parameter paged listing tool.

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 carries the full burden, yet it only echoes the offset and limit constraints already encoded in the schema (maximum 50). The required project_id is unelaborated and result_offset — a parameter that is easy to confuse with offset — is never explained, leaving two of four parameters with no meaning beyond their names.

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 a specific verb and resource ('List the service proposals this connector made on a project and their decisions') and explicitly separates this tool from read_service_change by stating it returns metadata only. An agent can distinguish this list operation from the detail-read sibling without opening either schema.

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 clearly routes the agent: use this for the list of proposals and their decisions, and use read_service_change when before/after values are needed. It also states that human admins see all proposals of the project. It does not distinguish this tool from other list-shaped siblings such as list_changes, so not a 5.

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