UNDERSTANDING — Delete a saved search you own. Priced B1 (single-entity synthesis) — $0.01 per call under pay-as-you-go; included in Understanding and Influence. See apis://prices.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Saved search id to delete, as list_saved_searches lists it. | |
| context | No | Optional: one sentence on why you are asking. Never used to rank; read only if a result is wrong. |
Changes observed during successful MCP inspections.
Input schema / properties / context / descriptionPrevious value: -"Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable."New value: +"Optional: one sentence on why you are asking. Never used to rank; read only if a result is wrong."Input schema / properties / id / descriptionAdded value: +"Saved search id to delete, as list_saved_searches lists it."Input schema / properties / contextAdded value: +{
+ "description": "Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable.",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is fully covered structurally. The description only adds the ownership precondition, which is mildly useful, but says nothing about irreversibility, cascade effects, or behavior when the caller doesn't own the search.
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?
Front-loads 'UNDERSTANDING —' branding followed by a long pricing sentence ('Priced B1 (single-entity synthesis) — $0.01 per call... See apis://prices') that does not help the agent select or invoke the tool. Only the middle clause is load-bearing, so the text is bloated relative to its information content.
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?
For a simple single-entity delete with full annotation coverage and 100% schema description coverage, the description is adequate. However, it omits error/ownership-failure behavior and offers nothing beyond the annotations on the destructive operation, so it is minimum viable rather than complete.
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%, and the schema already explains both 'id' and 'context' clearly, so the baseline is 3. The description adds no parameter-level meaning beyond the schema.
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 clear verb+resource: 'Delete a saved search you own.' The ownership scoping distinguishes it from siblings like list_saved_searches, run_saved_search, and save_search. Only the irrelevant branding/pricing prefix dilutes an otherwise precise purpose statement.
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?
No when-to-use guidance and no named alternatives (e.g., delete_list vs delete_saved_search). The 'you own' phrase is a precondition, not usage guidance. The agent must infer all context for calling it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.