Search PubMed and log every retrieved paper to the audit trail.
Args:
query: exact search string, sent to PubMed verbatim — no normalization
agent_id: which agent is asking, e.g. "aletheia:advocate"
max_results: how many papers to retrieve (default 5)
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| agent_id | Yes | ||
| max_results | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and openWorldHint=true, and the description explains why: every retrieved paper is written to the audit trail, so this is a read that still mutates local state. It also discloses that the query is passed verbatim with no normalization. Missing are rate limits, auth requirements, or the shape of the returned papers, which keeps it short of a 5.
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?
Front-loaded with the core action and side effect in the first sentence, then a compact per-argument breakdown. No filler, though the Python-docstring "Args:" formatting is slightly mechanical rather than prose.
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 3-parameter tool with no output schema, the description covers inputs and the audit side effect but says nothing about what a search actually returns (paper fields, result ordering, pagination/truncation when max_results is large). An agent knows how to call it but not what to expect back.
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 0%, so the description carries the burden and does so well: it explains query is sent verbatim (no normalization), gives an agent_id format example ("aletheia:advocate"), and confirms max_results defaults to 5. It adds real meaning beyond the bare schema types.
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?
States a specific verb and resource ("Search PubMed") and an additional effect ("log every retrieved paper to the audit trail"). The PubMed domain cleanly distinguishes it from siblings like search_biorxiv, search_europepmc, and search_clinicaltrials without needing to open any schema.
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?
Usage is implied by the subject matter — use this when you need PubMed literature — but there is no explicit when-to-use, when-not-to-use, or routing against overlapping siblings such as search_europepmc or search for general retrieval. An agent must infer the choice from the tool name alone.
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.