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

Annotations already declare readOnlyHint and idempotentHint, so the safety floor is covered; the description adds specifics by enumerating what it will never do (send, archive, change stages) and describing the returned shape (bounded rows, per-stage totals, sent/waiting/unsent counts, inbox replies). This is useful added context beyond the annotations rather than a restatement, though 'never sends/archives/changes stages' partially overlaps readOnlyHint.

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?

Four sentences, front-loaded with the core read action and filter before the filter-value guidance and return summary. Dense but each sentence carries distinct information; slightly longer than strictly needed for a three-parameter list tool.

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 values need not be spelled out, yet the description still summarizes them helpfully. Combined with annotations covering safety, the definition is essentially complete for an agent to call it correctly; only the limit parameter's semantics are left unaddressed.

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 only 33% (only stale_days is documented), so the description must carry the load and largely does by explaining the meaning of the non-obvious status values (ready_to_send, needs_answer, stale) and implying bounded output via 'bounded rows'. The limit parameter's cap/behavior is left unexplained, so it falls short of full compensation.

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 your saved jobs and application tracker with a status filter'), so the agent knows this is a list/read tool scoped to applications. It implicitly separates from the single-record sibling get_application, but never names or contrasts with it explicitly, keeping this short of a 5.

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?

Gives concrete scenario-to-filter mapping ('ready_to_send for approvals, needs_answer for outstanding questions, stale to review inactive applied rows'), which tells the agent when each mode applies. It does not state when this tool is preferable to search_jobs or get_application, so no exclusions or alternatives are provided.

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