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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered structurally. The description adds genuinely new context beyond that: the results are scoped to the signed-in homeowner's own jobs, each update is a short summary carrying only a job id, and details remain in InstaBids. The stated "Requires jobs:read" permission requirement is also information the annotations do not carry.

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 front-loaded with the core behavior and scope before moving to mechanics, permission, and limits, and no sentence is filler. The limit/default sentence duplicates the input schema, which is the only real redundancy. Overall it is tight and easy to parse.

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?

An output schema exists, so return-value detail need not be explained, and the description still characterizes the payload as short summaries with job ids. Combined with scope, cursor mechanics, and the jobs:read requirement, an agent has nearly everything needed. It does not say what happens with an invalid or expired cursor, which is the remaining operational gap.

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 both parameters are already documented in structured form, and the description largely restates them (cursor reuse, limit range 1-50, default 20). It does reinforce the cursor's role as a value returned by the previous call, which clarifies the incremental-polling idiom. With schema doing the heavy lifting, the baseline of 3 is appropriate.

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 ("Returns changes on ... jobs since an optional cursor") and enumerates exactly what is returned: new or changed bids, contractor messages and questions, and job status changes. That makes the resource scope unambiguous. It stops short of naming a sibling tool, so an agent must infer the boundary with get_job_status or list_bids on its own.

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 concrete invocation mechanics ("Pass the cursor returned by your previous call as since"), which implies the polling pattern this tool is meant for. However, it never states when to prefer this over siblings such as get_job_status or list_bids, nor any exclusion conditions. Usage is implied rather than guided.

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