Skip to main content
Glama

ctxstore — memory that follows you across models

Mark Salient (this matters now)

mark_salient

Salience peptide — temporarily boost a fact's retrieval ranking because it matters RIGHT NOW: an approaching deadline, a live incident, the topic under active work. The boost is small and FAST-DECAYING (max 1.4x, ~6-hour half-life — gone by tomorrow), unlike reinforce_fact which rewards confirmed outcomes on a weeks-long timescale.

Name the current situation in reason. Salience is ranking-only: it can never override tenant isolation, namespace grants, or privacy filters, and stacked peptide boosts are globally capped.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "reason": "<reason>"
    },
    "name": "mark_salient"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoExact fact key — marks the current version. Provide this OR fact_id.
reasonYesREQUIRED. Why this matters NOW, e.g. 'Snowflake migration deadline in 3 days' or 'debugging live incident #612'.
weightNoSalience strength 0-3 (default 1). Use ~0.5 for mildly topical, 1 for the current task, 2-3 for a live incident or imminent deadline.
fact_idNoUUID of the fact to mark salient (from search results). Provide this OR key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only state readOnly=false, destructive=false, idempotent=false, idle for an unusual ranking-mutation tool. The description supplies the missing behavior: bounded magnitude (max 1.4x), fast decay (~6-hour half-life, gone by tomorrow), ranking-only semantics that cannot override tenant isolation, namespace grants, or privacy filters, and a global cap on stacked boosts.

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?

The purpose and decay profile are front-loaded in the first sentence, and the sibling contrast follows immediately. Slight redundancy in repeating the reason guidance that the schema already gives, but there is no filler or padding.

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 4-param mutation with no output schema, the description covers magnitude, decay, precedence limits, and alternatives well. It doesn't state what happens when the key or fact_id does not resolve, or what the call returns, which is a small remaining gap.

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 coverage is 100%, so key/fact_id/weight/reason are all already documented, including the weight scale and the example reasons. The description's "Name the current situation in `reason`" only reinforces the schema rather than adding new meaning, so the baseline of 3 applies.

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

Purpose5/5

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

"Temporarily boost a fact's retrieval ranking" is a specific verb+resource with scope ('because it matters RIGHT NOW'), and it explicitly contrasts with reinforce_fact's weeks-long reinforced ranking. An agent can distinguish it from the other fact-level siblings without opening the schema.

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

Usage Guidelines5/5

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

It enumerates concrete triggering situations (approaching deadline, live incident, topic under active work) and names the alternative reinforce_fact along with the condition that selects it (confirmed outcomes vs. present urgency). The when/when-not contrast with the sibling is explicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.