search_articlesSearch PUBLISHED articles across Misar.Blog by keyword, tag, or author — including other creators' work. Use list_my_articles for your own drafts and unpublished posts.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Keyword query (min 2 characters) | |
| tag | No | Filter by tag | |
| limit | No | Results to return (1-20) | |
| author | No | Filter by author username |
Changes observed during successful MCP inspections.
Input schema / properties / author / descriptionPrevious value: -"Restrict to one author, by username."New value: +"Filter by author username"Input schema / properties / limit / descriptionPrevious value: -"Maximum results to return, 1-20. Defaults to 10."New value: +"Results to return (1-20)"Input schema / properties / q / descriptionPrevious value: -"Free-text query matched against title and body. Minimum 2 characters."New value: +"Keyword query (min 2 characters)"Input schema / properties / tag / descriptionPrevious value: -"Restrict to articles carrying this exact tag."New value: +"Filter by tag"Input schema / properties / author / descriptionPrevious value: -"Filter by author username"New value: +"Restrict to one author, by username."Input schema / properties / limit / descriptionPrevious value: -"Results to return (1-20)"New value: +"Maximum results to return, 1-20. Defaults to 10."Input schema / properties / q / descriptionPrevious value: -"Keyword query (min 2 characters)"New value: +"Free-text query matched against title and body. Minimum 2 characters."Input schema / properties / tag / descriptionPrevious value: -"Filter by tag"New value: +"Restrict to articles carrying this exact tag."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and open-world behavior, so safety is covered. The description adds genuinely useful scope context: results are restricted to PUBLISHED posts and include other creators' work, which the annotations do not convey.
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 with zero filler; the capability and the scoping constraint come first, followed by the routing hint. Every clause earns its place.
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 four-parameter, fully self-documented read-only search with no output schema, the description covers what an agent needs to select and call it. It could briefly note result ordering or that filters combine, but nothing essential is missing.
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 four parameters (q, tag, limit, author) are already fully documented in the schema. The description restates the filter dimensions but adds no syntax, format, or combination guidance beyond it, making the baseline 3 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?
States a specific verb (Search) and resource (PUBLISHED articles) plus the searchable dimensions (keyword, tag, author) and the cross-creator scope. It is immediately distinguishable from siblings like list_my_articles or get_article.
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?
Explicitly names the alternative tool (list_my_articles) and the condition that selects it (your own drafts and unpublished posts). The routing decision is fully specified without inference.
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.