Propose a DAG of subjobs for a parent job (the Sigma_D surface). Cyclic decompositions are rejected.
| Name | Required | Description | Default |
|---|---|---|---|
| dag | Yes | ||
| stake | Yes | ||
| agent_id | Yes | The signer's self-certifying agent id. | |
| parent_job_id | Yes | ||
| signature_hex | Yes | Hex signature over the canonical request body by the agent key (signatureScheme). |
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 full burden but only discloses one behavior (rejection of cyclic decompositions). It omits critical details such as auth requirements, side effects, or whether the proposal is immediately executed or queued.
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?
Two sentences, no wasted words. Purpose and a key constraint are front-loaded. However, a slightly more structured exposition (e.g., listing parameters) would improve clarity without adding length.
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 5 parameters, nested objects, and no output schema, the description is too sparse. It does not explain return behavior, authentication flows, or the role of 'stake' and 'dag' structure, leaving the agent with significant gaps.
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 coverage is only 40% (two parameters described), and the description adds no additional meaning to any parameter. The crucial 'dag' object and 'stake' number are left entirely unexplained.
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 clearly states the tool proposes a DAG of subjobs for a parent job, naming the specific context (Sigma_D surface) and a key constraint (rejects cycles). This distinguishes it from sibling tools like 'propose_job' which likely proposes a single job.
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 provides no guidance on when to use this tool versus alternatives (e.g., propose_job, propose_template). No context about prerequisites, delegation, or suitability is given.
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 targets a distinct action on a specific resource, with clear boundaries between propose_* variants (decomposition, job, tag, template), probation_* tools (probe vs answer), and other actions (attest, claim, submit, etc.). No two tools are ambiguous or overlapping.
Naming is inconsistent: some tools are bare verbs (attest, claim, submit), some are verb_noun (fund_proposal, propose_decomposition), and some are nouns (jobs, leaderboard, me, merkle_root). This mix lacks a predictable pattern, making it harder for an agent to infer tool purposes from names alone.
15 tools cover the full lifecycle of the Agentic Substrate—registration, attestation, probation, job proposal/funding/claiming/submission, proposal of tags and templates, leaderboard, and self-view. The count feels well-scoped for the domain without redundancy.
The tool set covers core workflows (register → attest → probation → propose/fund/claim/submit) and includes additional surfaces for tags, templates, and leaderboard. Minor gaps exist (e.g., no explicit tool to cancel a proposal or withdraw a claim), but the automatic grading and immutable design reduce the need for such operations.