Skip to main content
Glama
Sign In

AANet

by space.aanet
OverviewDiscussionsAdmin

aanet_append_file

Append one entry to a file without touching what's already there, creating the file if it doesn't exist yet — use aanet_write_file instead when you need to replace the whole file. Typical use: a shared log or running notes file multiple sub-agents contribute to. Fires a file_write webhook event on success. Rejected with 413, before writing or charging, if the resulting file (existing content + this append) would exceed 1 MiB. Accepts the same fence guard as aanet_write_file. Returns {path, appended, etag}.

Input Schema

NameRequiredDescriptionDefault
pathYesVirtual file path within the workspace.
fenceNoFencing token returned by aanet_acquire_lock/aanet_renew_lock. If another sub-agent has acquired that lock since, the call is rejected with 409 STALE_FENCE (free) instead of writing as a stale holder. Omit for an unguarded write.
stampNoSame attribution-comment option as on aanet_write_file, applied to this appended entry.
api_keyYesBearer credential for this workspace: either the owner_key returned once by aanet_create_workspace/aanet_create_trial_workspace, or a sub-key returned by aanet_mint_subkey. Sent under the hood as `Authorization: Bearer <api_key>`. Owner-only tools reject a sub-key with a 403.
contentYesText to append as a new entry — the existing content is kept.
if_matchNoThe file's current etag, for the same conflict-detection purpose as on aanet_write_file.
fence_lockNoName of the lock the fence belongs to; defaults to the file path itself. Needs fence.
workspace_idYesThe workspace_id from aanet_create_workspace or aanet_create_trial_workspace.
idempotency_keyNoOptional retry-safety token (any unique string, e.g. a UUID). If a call times out and you repeat it with the same key and the same arguments, the first successful result is returned again without charging a second time. Keys are remembered for 24 hours, per sub-key. Reusing a key with different arguments is an error (code=IDEMPOTENCY_KEY_REUSED).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / fence
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Fencing token returned by aanet_acquire_lock/aanet_renew_lock. If another sub-agent has acquired that lock since, the call is rejected with 409 STALE_FENCE (free) instead of writing as a stale holder. Omit for an unguarded write.",
+  "title": "Fence"
+}
    • addedInput schema / properties / fence_lock
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Name of the lock the fence belongs to; defaults to the file path itself. Needs fence.",
+  "title": "Fence Lock"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 255,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional retry-safety token (any unique string, e.g. a UUID). If a call times out and you repeat it with the same key and the same arguments, the first successful result is returned again without charging a second time. Keys are remembered for 24 hours, per sub-key. Reusing a key with different arguments is an error (code=IDEMPOTENCY_KEY_REUSED).",
+  "title": "Idempotency Key"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / stamp
      Added value: +{
+  "default": false,
+  "description": "Same attribution-comment option as on aanet_write_file, applied to this appended entry.",
+  "title": "Stamp",
+  "type": "boolean"
+}
  4. Changed5 schema fields changed
    • addedInput schema / properties / api_key / description
      Added value: +"Bearer credential for this workspace: either the owner_key returned once by aanet_create_workspace/aanet_create_trial_workspace, or a sub-key returned by aanet_mint_subkey. Sent under the hood as `Authorization: Bearer <api_key>`. Owner-only tools reject a sub-key with a 403."
    • addedInput schema / properties / content / description
      Added value: +"Text to append as a new entry — the existing content is kept."
    • addedInput schema / properties / if_match / description
      Added value: +"The file's current etag, for the same conflict-detection purpose as on aanet_write_file."
    • addedInput schema / properties / path / description
      Added value: +"Virtual file path within the workspace."
    • addedInput schema / properties / workspace_id / description
      Added value: +"The workspace_id from aanet_create_workspace or aanet_create_trial_workspace."
  5. First observed

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: it discloses the file_write webhook event, the 1 MiB cap checked before writing or charging, the fence guard shared with aanet_write_file, and the return shape {path, appended, etag}. That is exactly the behavioral context an agent needs for a mutating tool with zero annotation coverage.

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

Conciseness5/5

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

Front-loaded with what the tool does and how it differs from the sibling, then layers in use case, side effects, limits, and return shape in compact order. Every sentence, including the error codes and return object, earns its place.

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

Completeness5/5

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

For a 9-parameter mutation tool with no annotations and no output schema, the description covers purpose, alternative, typical usage, side effects, failure modes, and the exact return object. Nothing material for a correct call is missing.

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 all nine parameters are already documented in structured data, establishing the baseline of 3. The description references the fence guard and stamp option only by pointing at aanet_write_file, adding cross-tool context but no new syntax or format detail beyond the schema.

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?

States a specific verb (append) and resource (one entry to a file), plus the non-destructive semantics ('without touching what's already there'). It explicitly names the sibling it is not (aanet_write_file) and the condition that separates them, so an agent can route correctly without opening the schemas.

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?

Explicitly says when to use this tool instead of aanet_write_file, gives a concrete typical use case (shared log / running notes with multiple sub-agents), and describes rejection conditions (413 for >1 MiB) before side effects occur. Nothing about selection is left to inference.

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

All AANet toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources