Rafe Blandford — career and writing

Check for published evidence of a topic

check_experience

Read-onlyIdempotent

Ask whether this site publishes anything evidencing a topic — a technology, a sector, a discipline, a kind of leadership.

Returns supported, partial or not_found, a plain-language statement, and source URLs you can check.

⚠️ PASS A SUBJECT, NOT A SENTENCE. Matching is on whole words, so a long phrase fails to match and comes back not_found even when the subject inside it is well evidenced. 'product strategy' is supported here; 'product strategy across a portfolio of consumer-facing digital products' returns not_found. Two to four words. If you are testing a job requirement, break it into its subjects and check each one.

⚠️ Read the statement carefully before answering the person who asked. not_found means NOTHING PUBLISHED ON THIS SITE EVIDENCES the topic. It is a fact about a selective corpus, not about Rafe — he has done a great deal that is not written up here. Every response carries his LinkedIn, which is the fuller record, and his email. Do not turn a not_found into 'Rafe has no experience of X'.

Input Schema

Name	Required	Description	Default
`topic`	Yes	A short subject, 2–4 words — 'composable architecture', 'insurance', 'team leadership'. NOT a sentence or a whole job requirement: long phrases match nothing and return a misleading not_found.

Output Schema

Name	Required	Description
`topic`	Yes
`corpus`	No
`status`	Yes
`evidence`	Yes
`elsewhere`	Yes
`statement`	Yes	Plain-language answer. Pass this on as written — the not_found wording is deliberately about the corpus, not the person.
`scope_note`	Yes
`alias_applied`	No	Set when the topic as typed matched nothing and a declared alias was used instead — e.g. CTO to the published title Chief Technology & Product Officer. The evidence below is for `to`, not for what was asked. Say so if you pass the answer on.
`also_mentions`	No	NOT EVIDENCE. Items where the words merely occur. These did not contribute to `status` and must not be reported as though the site evidences the topic. Offered only as somewhere to look next.
`related_topics`	No	NOT EVIDENCE for the topic asked. Only on partial/not_found. Other topics the site declares that are near matches on WORDING — a route to a better query, never support for this one. Do not describe these as related evidence.
`shown_in_the_work`	No	Evidence word matching cannot see. Only on partial or not_found. Published work that demonstrates the subject without naming it. Read two or three items and weigh them on what they show, citing them; the status records only the word match.
`declared_expertise`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

addedOutput schema / properties / shown_in_the_work

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Evidence word matching cannot see. Only on partial or not_found. Published work that demonstrates the subject without naming it. Read two or three items and weigh them on what they show, citing them; the status records only the word match.",
+  "title": "Shown In The Work"
+}

First observedAug 8, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, but the description adds material beyond them: the three possible outcomes (supported/partial/not_found), the fact that responses carry source URLs, and critically the whole-word matching failure mode that can produce a misleading not_found. The warning about not over-reading not_found as 'no experience of X' is exactly the kind of interpretive context annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded correctly: purpose, then return shape, then the two warnings. Sentences are dense but each carries distinct value, though the two ad-monition blocks are lengthy relative to the single-parameter surface and could be tightened slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read tool with an output schema and full annotations, the description covers purpose, argument shape, return semantics and the main misreading risk. The only gap is routing against sibling tools like get_evidence, which is left unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With one parameter at 100% schema coverage the baseline is 3, and the description earns an increment by adding contrastive example pairs ('product strategy' works vs. the long phrase that returns not_found) that clarify the 2-4 word constraint more sharply than the schema text alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific verb and resource: asking whether the site publishes anything evidencing a topic, with concrete scope examples (technology, sector, discipline, leadership). It is clear and unambiguous, but it never names or differentiates against the closest sibling, get_evidence, so an agent must infer which one to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context: pass a short subject, break a job requirement into its subjects and check each one, so the agent knows how this tool is meant to be applied. It stops short of explicit when-not-to-use or pointing to alternatives such as search_writing or map_role_requirements.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Rafe Blandford — career and writing tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?