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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description correctly aligns with that. It adds behavioral context by explaining the composed stream includes per-company job items with flags like isStarred meaning the user unstarred a company since, and that 'job_of_the_day' is a discovery candidate. It also mentions entries are chronological newest first, which is useful. The only minor gap is not detailing the exact return schema or error behavior, but annotations cover the safety profile.

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 detailed but not overly long; it front-loads the key purpose and composition, then provides usage guidance. It could be slightly more concise, but every sentence adds value, explaining entry kinds and usage. It's well-structured for an agent 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?

Given the tool's complexity (multiple entry kinds, flags, and pagination), the description is thorough. It covers the composition of the feed, the meaning of key fields, and how to use pagination. With annotations covering safety and no output schema needed, the description is complete for an agent to call it correctly.

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 coverage is 100%, so the schema already documents both parameters. The description adds meaning by explicitly stating 'Pass nextCursor back to page deeper; omit it for the newest page' and mentioning pageSize default and max, reinforcing the schema. However, the description doesn't add much beyond that, so baseline 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 states a specific verb ('View') and resource ('dashboard feed'), and distinguishes it from siblings by describing it as a composed stream with specific entry kinds. It clearly explains the feed's purpose as a notification layer, which differentiates it from other get_* tools like get_digests.

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 provides explicit usage guidance: it says to poll on the user's schedule, to act as a notification layer, to save interesting roles via save_job, and to brief the user. It also explains how to use the cursor parameter for pagination, and mentions that blog and broadcast entries are 'usually skim' implying when to skip them. This is explicit and actionable.

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