PubMed Scraper: Articles, Abstracts & Evidence Table to Excel

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

Annotations already declare read-only, non-destructive, open-world, non-idempotent, so the description focuses on what annotations cannot carry: per-article pricing, which filters are applied before billing, that PRISMA counts still report removed records, the run_max_items vs maxResults billing interaction, the 300s timeout ceiling, and that long text output is trimmed to whole items. The only gap is no statement about how failures or partial results surface beyond the timeout hint.

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 purpose, then alternatives, then parameter behavior, then runtime/cost — a sensible order for an 18-parameter tool, and nearly every sentence carries information. It is long and repeats billing language already present in the maxResults and retractedArticles schema descriptions, which costs it a point.

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 an 18-parameter tool with no output schema, the description supplies the return field list, the envelope shape {actor, count, items}, the structuredContent trimming rule, latency expectations, and where Excel/PRISMA/RIS artifacts are stored. Combined with full schema coverage and annotations, an agent has everything needed to call it and interpret the result.

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 100%, so baseline is 3, but the description adds genuinely non-obvious semantics: queries accept field tags and are de-duplicated across queries, retractedArticles=flag bills flagged rows while exclude does not, and sampleSizeConfidence should be treated as unverified at low values. The subtle warning that raising maxResults can bill more than run_max_items returns is the kind of interaction the schema alone cannot convey.

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?

Specific verb and resource: 'Run one or more PubMed queries and return a screening-ready evidence table', with the row schema (PMID, journal, study design, sample size, retraction status) enumerated. It explicitly distinguishes itself from literature_search, clinical_trial_leads and reference_checker by scope and data source, so an agent can route between them without opening a 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?

States the positive condition ('biomedical/clinical and you need reproducible PubMed queries or design filters') and four explicit when-not cases with the sibling to use instead. 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.