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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, yet the description adds substantial context: coverage is limited to writes owned by this topic (contributions, legacy notes, optional work), cross-topic assessments are excluded, baseline imports do not reconstruct missing history, and a reported assessment is not a validated verdict. These are genuine behavioral caveats an agent needs before trusting the feed.

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?

Read is front-loaded as the opening action, and each sentence carries distinct information. The prose is dense and somewhat jargon-heavy ('optional work,' 'exact target reads,' 'page window'), which slightly taxes comprehension, but there is no filler.

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 and only partial parameter coverage, the description does the heavy lifting by explaining feed scope, cursor lifecycle, and explicit coverage limitations. It stops short of describing page/return shape or the per_page bound, but the essential operational picture is present.

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 only 33%: cursor is documented in the schema, while orbit_id and per_page carry no description. The text reinforces that the cursor is opaque and should be retained for polling and that everything is scoped to one Orbit, but it says nothing about per_page (pagination size) or orbit_id semantics, so it only partially compensates for the coverage gap.

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?

States a specific verb and resource: 'Read a paginated public change feed scoped to one Orbit.' The scope (single Orbit, cursor-driven) is clear and distinguishes it from read_contribution/search_contributions, though it never names those siblings explicitly.

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?

Provides meaningful workflow guidance: follow next_cursor to finish the page window and retain the cursor for later polling. It also notes that cross-topic incoming assessments must be reached 'through exact target reads,' implying an alternative path. However, it never explicitly contrasts this feed with sibling reads or states when not to use it.

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