UNDERSTANDING — List the saved searches you own (name, criteria, when last run, how many matches are tracked). 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 |
|---|---|---|---|
| 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 / 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 readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful context beyond annotations: the pricing tier (B1, $0.01/call), billing umbrella (Understanding/Influence), and the synthesized return fields. It stops short of describing pagination or result limits.
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 the category and the core action, then appends the return fields and pricing. The pricing sentence is somewhat dense, but every clause carries information an agent may need. Minor verbosity from the pricing/pointer sentence.
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?
A simple read-only listing tool with one optional parameter and no output schema; the description compensates by naming the returned fields. Pricing and category are covered, leaving only pagination/limits unstated, which is a minor gap for this complexity level.
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 single 'context' parameter is fully documented in the schema, so the baseline is 3. The description adds nothing about the parameter, nor does it need to given the complete schema, but it misses the chance to reinforce that context is never used for ranking.
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 saved searches) plus scope ('you own'), and enumerates the returned fields (name, criteria, last run, match count). An agent can distinguish it from siblings like save_search, delete_saved_search, and run_saved_search without opening any schema.
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 purpose implies when to call it, but there is no explicit guidance on when to use this versus list_lists, list_watches, or run_saved_search, and no exclusions stated. Usage is only implied by the tool's listing nature.
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.