Skip to main content
Glama

set_project_knowledge

DestructiveIdempotent

Stores and upserts structured project facts by key, updating existing entries so agents can record deploy URLs, stack conventions, and gotchas for later retrieval.

Instructions

Write a structured fact to project knowledge. UPSERT by key — calling with same key updates the existing entry. Stores deploy URLs, stack conventions, gotchas. These facts are visible via get_project_knowledge.

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": {
      "project_id": "<project_id>",
      "key": "<key>",
      "value": "<value>"
    },
    "name": "set_project_knowledge"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesSlug key for UPSERT (e.g. 'deploy-url', 'stack-convention'). Same enforced pattern as remember: ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — hyphens only, no colons; a colon-delimited key is refused, not normalised.
tagsNoAdditional tags for filtering.
valueYesThe knowledge to store (markdown, max 4000 chars).
categoryNoOptional category: deploy, stack, conventions, gotchas, api, auth, etc.
thread_idNoThread identifier. Auto-populated from the runner state file when omitted.
project_idYesProject ID to store knowledge for.
source_urlNoOptional URL/path to the source of this knowledge.
attach_contextNoWhen false, disables auto-injection of thread_id and source_task_id.
source_task_idNoUUID of the Mesh task that produced this fact. Auto-populated from the runner state file when omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.6
    • changedInput schema / properties / key / description
      Previous value: -"Slug key for UPSERT (e.g. 'deploy-url', 'stack-convention'). Same enforced pattern as remember: ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — hyphens, NEVER colons; a colon-delimited key is REFUSED, not normalised."New value: +"Slug key for UPSERT (e.g. 'deploy-url', 'stack-convention'). Same enforced pattern as remember: ^[a-z0-9][a-z0-9-]*[a-z0-9]$ — hyphens only, no colons; a colon-delimited key is refused, not normalised."
  2. First observedv0.1.1

TDQS

A3.7/5.0
Behavior4/5

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

The description discloses the key behavioral fact beyond annotations: calling with the same key updates rather than duplicates (consistent with idempotentHint=true), which explains the destructiveHint=true overwrite in practical terms. It omits auth requirements and any statement about what prior value is lost on overwrite, so it stops short of fully carrying the mutation burden.

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?

Three short sentences, front-loaded with the action and the UPSERT rule before the content examples. No filler; the only mild redundancy is restating the read path that the tool name already implies.

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 9-parameter write tool with no output schema and full schema coverage, the description covers action, idempotency behavior, intended content, and retrievability. It could be stronger by clarifying the boundary with `remember` and the consequences of overwriting an existing key, but nothing essential is missing for correct invocation.

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 every one of the 9 parameters is already documented in the schema, including the key slug pattern, the 4000-char value limit, and thread_id/source_task_id auto-population. The description adds only the UPSERT framing, which the schema key field already reinforces — baseline 3 applies.

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?

Specific verb+resource ("Write a structured fact to project knowledge") plus explicit UPSERT-by-key semantics, which tells the agent this is a write/update tool rather than a pure insert. It names the read counterpart get_project_knowledge, but never distinguishes itself from the very similar `remember` sibling except obliquely inside the schema's key description.

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

Usage Guidelines3/5

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

"Stores deploy URLs, stack conventions, gotchas" gives concrete content cues, and "visible via get_project_knowledge" points at the companion read tool. However there is no explicit when-to-use vs when-not-to-use guidance, and with `remember` sitting in the sibling list an agent would reasonably want a rule for choosing between them.

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