Coil Scanner

save_memory

Idempotent

Storefront: stores one short shopping preference for this session's cart, for example which product or billing period the shopper prefers. Coil stores it keyed to this MCP session (Mcp-Session-Id), scoped to this MCP session only, keeps it one day and then deletes it; without a session nothing is stored; a repeated key replaces its value and at most 40 entries are kept. It is not conversation storage. Access: free, no key.

Input Schema

TableJSON Schema

Name	Required	Description
`key`	Yes	Short name of the preference, e.g. billing_period (1-64 characters).
`value`	Yes	The preference itself, e.g. yearly (1-280 characters).
`category`	No	Optional grouping label, e.g. billing (up to 32 characters).

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 16, 2026
- addedInput schema / properties / category / description
```
Added value: +"Optional grouping label, e.g. billing (up to 32 characters)."
```
- addedInput schema / properties / category / maxLength
```
Added value: +32
```
- addedInput schema / properties / key / description
```
Added value: +"Short name of the preference, e.g. billing_period (1-64 characters)."
```
- addedInput schema / properties / key / maxLength
```
Added value: +64
```
- addedInput schema / properties / value / description
```
Added value: +"The preference itself, e.g. yearly (1-280 characters)."
```
- addedInput schema / properties / value / maxLength
```
Added value: +280
```
- addedInput schema / required
```
Added value: +[
+  "key",
+  "value"
+]
```
AddedSep 2, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already declare a non-destructive, idempotent write, and the description adds substantial context beyond them: session-keyed storage, no-session no-op, one-day TTL then deletion, last-write-wins on repeated keys, and a hard cap of 40 entries. This is exactly the lifecycle behavior an agent needs before writing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and the sentences are dense with distinct facts (scope, TTL, no-session behavior, overwrite, cap), so little is wasted. The single long semicolon-chained block is harder to scan than a short bulleted breakdown would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating tool with an output schema absent, the description covers the essentials: scope, lifetime, overwrite semantics, capacity limit, and cost. It does not describe the success/failure response or what happens when the 40-entry cap is reached, which are minor residual gaps given annotations cover the safety profile.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so key, value, and category are already documented with examples and length limits in the schema. The description restates the notion of a short preference but adds no syntax, format, or constraint detail beyond the schema, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource: stores one short shopping preference keyed to the cart for the session, with illustrative examples (product, billing period). It distinguishes itself from generic memory via 'It is not conversation storage', but never names its natural counterpart recall_memories, so the sibling boundary is only partially drawn.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear situational context (session-scoped cart preferences, one day lifetime) and one explicit exclusion ('not conversation storage'; no session means nothing is stored). It stops short of routing the agent to recall_memories for retrieval or stating when saving is unnecessary, so usage is implied rather than fully prescribed.

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

All Coil Scanner tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?