fm_repositionUpdate your view on an open call as the signal evolves. Same qualitative rule as opening one.
| Name | Required | Description | Default |
|---|---|---|---|
| lean | No | ||
| rationale | No | ||
| tenant_slug | Yes | ||
| access_token | Yes | ||
| position_key | Yes | From fm_book_status or fm_open_position. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHint=false, confirming a mutation. The description adds 'Update your view', which is consistent but does not disclose any additional behavioral traits such as required permissions, side effects on other positions, rate limits, or success/failure indicators. The description adds minimal value beyond the annotations.
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 short sentences, which is appropriately concise. However, the second sentence ('Same qualitative rule as opening one') is cryptic and wastes space without adding value. The structure front-loads the main purpose but sacrifices clarity for brevity.
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?
Given the complexity (5 parameters, mutation, no output schema, low schema coverage), this description is incomplete. It does not explain what the call status becomes after repositioning, what the parameters mean, what information the tool returns, or any behavioral nuances. The agent would have to infer too much from the name and schema alone.
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 only 20% (only position_key has a description). The tool description does not mention any parameters at all. It fails to explain the meaning or usage of lean, rationale, tenant_slug, or access_token. A description for a 5-parameter tool with low schema coverage must compensate, but it provides zero parameter semantics.
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 title 'Reposition a call' combined with the description 'Update your view on an open call as the signal evolves' clearly identifies the tool as a mutation on an existing position. It implicitly differentiates from sibling tools like fm_open_position (create) and fm_close_position (close), though it lacks explicit scoping. The phrase 'Same qualitative rule as opening one' is ambiguous and slightly undermines clarity.
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 suggests using this tool when the signal changes ('as the signal evolves'), but it provides no explicit guidance on when not to use it or which alternative to prefer. The cryptic reference to 'Same qualitative rule as opening one' does not clearly direct the agent toward fm_open_position or any other sibling. No when-not-to or alternative scenarios are stated.
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.
Every tool has a clearly distinct purpose, with detailed descriptions that prevent ambiguity. Even similar tools like search_articles, search_declassified, and search_unified target different corpora, and the publisher tools are well-separated. No overlap that would confuse an agent.
All tool names follow a consistent verb_noun pattern with snake_case, using clear prefixes like get_, search_, subscribe_, publisher_, fm_, digest_, etc. The naming is predictable and systematic, making it easy for an agent to infer functionality.
At 37 tools, the count is higher than the typical 3-15 range for a coherent set, but the server covers a wide domain (content retrieval, podcast management, fund manager book, embedder network, etc.). Each tool earns its place, though the set could be slightly reduced by merging some rare-use tools.
The tool surface is comprehensive for the server's purpose—search, audio, subscriptions, publisher workflows, and special features like the Divergence Index. Minor gaps exist (e.g., no explicit unsubscribe tool, no article update/delete), but they are not critical for core workflows.