Submit a letter to the desk. If the desk answers, the exchange may be published on the Letters page (excerpted, initialed) — through the desk's normal editorial process, never directly. Requires the reader key.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | The reader key issued by the desk's operator. | |
| from | No | Initials or short byline, e.g. 'M.P.'. | |
| text | Yes | The letter (plain text, up to ~4000 chars). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It does well by explicitly stating that publication is never direct, is subject to the desk's normal editorial process, and may be excerpted and initialed. This meaningfully informs an agent's expectations about side effects, though it does not mention any immediate return or confirmation behavior.
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?
The description is two sentences with no filler. The primary action is front-loaded, and the second sentence adds necessary editorial-process context that prevents the agent from assuming direct publication.
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?
For a simple three-parameter submit tool with no output schema and no annotations, the description covers the core behavior, the reader-key requirement, and the non-obvious publication pipeline. It is slightly light on what happens immediately after submission, but it is otherwise sufficient to call the tool correctly.
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 description coverage is 100%, so the schema already documents key, from, and text. The description adds only that the reader key is required, which restates a schema requirement rather than adding new parameter semantics. Baseline 3 is appropriate.
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?
The description uses a specific verb and resource: 'Submit a letter to the desk.' It also clarifies the publishing nuances (excerpted, initialed, through editorial process), which distinguishes it clearly from read-only siblings like list_letters and verify_piece.
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 description states a prerequisite ('Requires the reader key') and describes the outcome if the desk answers, but it gives no explicit guidance about when to choose this tool over alternatives or when not to use it. No sibling comparisons or exclusion conditions are provided.
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.
Each tool maps to a distinct resource or action: list versus get for corpus discovery, chain versus claim ledger versus storyboards for chain analysis, framing index versus boxscore for statistics, and submit/report/propose for reader input. Even adjacent pairs like get_audit and verify_piece are clearly separated by their different purposes.
All tools follow a consistent verb_noun snake_case pattern, with get_* for detailed retrieval, list_* for summaries, and action verbs for reader-facing inputs. The verb choice reliably signals the operation type throughout.
At 15 tools, the set sits at the upper end of the ideal range, but every tool addresses a distinct facet of the desk's public surface: discovery, deep detail, provenance, coverage monitoring, and reader interaction. No tool feels redundant or decorative.
The surface covers discovery, retrieval, chain analysis, provenance verification, corrections, and reader interaction, forming a coherent workflow with no dead ends. Minor gaps exist: boxscore days are only enumerated off-server, and letters are exposed only as excerpts rather than individually retrievable records.