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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description only adds the shape of the returned rows, with no mention of ordering guarantees, empty-state behavior, or pagination beyond the schema's limit bound.

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?

Two sentences, zero filler, and the primary purpose is front-loaded before the workflow context. Every clause earns its place by either defining the resource or routing the agent to downstream tools.

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 compensates by naming the returned fields and the 'most recent' ordering, and it places the tool in the workflow chain. Only minor gaps remain, such as what happens when the user has no saved scrapes.

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% with a single well-documented 'limit' parameter (default 10, range 1-20), so the schema carries full semantic load. The description adds nothing about the limit parameter; baseline 3 applies.

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 (list the user's most recent saved scrapes) and even enumerates the returned fields (title, page, row count, id). It separates the resource from sibling list tools like list_my_runs and list_my_schedules by naming 'saved scrapes' explicitly, though it never directly contrasts itself with those siblings.

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?

'A saved scrape is the starting point for schedule_extraction and get_run_results' tells the agent exactly why and when it would call this tool: to obtain a scrape id needed to feed extraction or run-result lookups. No explicit exclusions or when-not-to-use guidance is given, which keeps it short of a 5.

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